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. 3-RESID-POST-AA
    6. 95196
    Prev
    Next
    INDEX
    Explanations

    ance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    proof
    -0.07
     anonymously
    -0.06
     Ip
    -0.06
    川
    -0.06
     üzer
    -0.06
     kostenlos
    -0.06
     Bolshevik
    -0.06
     
    -0.06
    ails
    -0.06
    ableView
    -0.06
    POSITIVE LOGITS
     Lance
    0.24
     lance
    0.19
     Vance
    0.15
    ance
    0.14
     sublicense
    0.11
    ANCE
    0.10
    ances
    0.09
    nce
    0.09
     VAN
    0.08
    .Invoke
    0.08
    Activations Density 0.002%

    No Known Activations