© 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. 126702
    Prev
    Next
    INDEX
    Explanations

    common

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “common” in mathematical phrases (e.g. common factor, common divisor, lowest common denominator).

    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
     ->
    -0.07
    AMED
    -0.07
     CHARSET
    -0.07
    _dtype
    -0.07
    (Local
    -0.06
    BitFields
    -0.06
    EditText
    -0.06
     EditText
    -0.06
     knitting
    -0.06
    esture
    -0.06
    POSITIVE LOGITS
     edip
    0.06
    .yaml
    0.06
     convertView
    0.06
     mise
    0.06
    汉
    0.06
    仅
    0.06
    ับร
    0.06
    _alt
    0.05
    Air
    0.05
     LT
    0.05
    Activations Density 0.002%

    No Known Activations