© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 88962
    Prev
    Next
    INDEX
    Explanations

    time/sequence words

    np_max-act · gemini-2.0-flash

    This neuron never activates on any tokens—it does not detect or respond to anything.

    oai_token-act-pair · o4-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
    за
    -0.06
    μου
    -0.06
     didn
    -0.06
     wie
    -0.06
    ��
    -0.06
    rej
    -0.06
    COM
    -0.06
    اتف
    -0.06
    ectomy
    -0.06
    .population
    -0.06
    POSITIVE LOGITS
    	DBG
    0.06
    \data
    0.06
    grupo
    0.06
     xt
    0.06
     RFC
    0.06
     установ
    0.06
     Camel
    0.06
     Chan
    0.06
     відч
    0.06
    _DEV
    0.06
    Activations Density 0.089%

    No Known Activations