© 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. 92620
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron fires whenever it sees a simple single‐digit addition expression (e.g. “1+2”).

    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
     Jer
    -0.07
     analysis
    -0.07
    амп
    -0.07
    Birth
    -0.07
    yses
    -0.07
    i
    -0.07
     meses
    -0.07
     chest
    -0.06
    searchModel
    -0.06
    tip
    -0.06
    POSITIVE LOGITS
    entially
    0.07
    respons
    0.06
     lstm
    0.06
    γκα
    0.06
     ситуа
    0.06
     ö
    0.06
     �
    0.06
    /table
    0.06
    IFORM
    0.06
    .normalized
    0.06
    Activations Density 0.011%

    No Known Activations