© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13639
    Prev
    Next
    INDEX
    Explanations

    comparisons and descriptions

    np_max-act · gemini-2.0-flash

    This neuron lights up on copular “is”-style constructions—i.e. definitional or explanatory statements linking a subject (“X is Y”) with a descriptor or participial phrase.

    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
     opinions
    -0.07
     ledna
    -0.07
    Một
    -0.06
     internacional
    -0.06
     Perry
    -0.06
    Ι
    -0.06
    RCT
    -0.06
     “
    -0.06
     <↵
    -0.06
    OTES
    -0.06
    POSITIVE LOGITS
    orough
    0.06
    ionario
    0.06
     통
    0.06
    .cpu
    0.06
    actively
    0.06
    ー�
    0.06
     تول
    0.06
     Lines
    0.06
    buquerque
    0.06
    _Start
    0.06
    Activations Density 0.178%

    No Known Activations