Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88880
    Prev
    Next
    INDEX
    Explanations

    initial, first

    np_max-act · gemini-2.0-flash

    This neuron lights up on discourse markers and process-step words that signal sequencing or evaluation—e.g. “first,” “initially,” “after,” “until,” “review,” “analysis,” “tasting,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions about educational policies and female empowerment in education.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bah
    -0.07
    DTD
    -0.06
    Tex
    -0.06
    乘
    -0.06
    适
    -0.06
    jí
    -0.06
    	LOG
    -0.06
     bred
    -0.06
     profound
    -0.06
    وس
    -0.06
    POSITIVE LOGITS
     plataforma
    0.07
     строитель
    0.07
     discontent
    0.07
     trophies
    0.06
    \Customer
    0.06
     وفي
    0.06
     Mädchen
    0.06
     Ventures
    0.06
    _MOV
    0.06
     kvin
    0.06
    Activations Density 0.096%

    No Known Activations