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. 15-RESID-POST-AA
    6. 61564
    Prev
    Next
    INDEX
    Explanations

    requests and responses

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ISPs
    -0.07
    localObject
    -0.07
     bağlı
    -0.07
     ウ
    -0.06
     Rounds
    -0.06
     unters
    -0.06
     lobbyists
    -0.06
     Alam
    -0.06
    ÔNG
    -0.06
    ичес
    -0.06
    POSITIVE LOGITS
    -го
    0.06
     striving
    0.06
     nemoh
    0.06
     personalize
    0.06
    √
    0.06
    efined
    0.06
    achinery
    0.06
    eği
    0.06
    ue
    0.06
    sterreich
    0.06
    Activations Density 0.054%

    No Known Activations