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. 77487
    Prev
    Next
    INDEX
    Explanations

    conversational/narrative text

    np_max-act · gemini-2.0-flash

    questions asking about the assistant's personal attributes or identity (age, location, appearance, name).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     Crowd
    -0.07
     Fallon
    -0.06
     cvs
    -0.06
     fists
    -0.06
     佛
    -0.06
    _counter
    -0.06
     듯
    -0.06
     mig
    -0.06
     درد
    -0.06
     evolves
    -0.06
    POSITIVE LOGITS
    осред
    0.07
    asley
    0.07
    annotation
    0.06
     Luca
    0.06
     γρα
    0.06
    olesterol
    0.06
     м
    0.06
    andidates
    0.06
     spotting
    0.06
    @gmail
    0.06
    Activations Density 0.050%

    No Known Activations