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. 19-RESID-POST-AA
    6. 29338
    Prev
    Next
    INDEX
    Explanations

    centrifug

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     représ
    -0.06
    Ich
    -0.06
    �
    -0.06
    ستی
    -0.06
     Mad
    -0.06
     Ble
    -0.06
    baz
    -0.06
    _epsilon
    -0.06
     ole
    -0.06
     aide
    -0.06
    POSITIVE LOGITS
     centrif
    0.07
     workshop
    0.06
    enerative
    0.06
    expense
    0.06
     creek
    0.06
    .points
    0.06
     oppression
    0.06
    nění
    0.06
    ويل
    0.06
    že
    0.06
    Activations Density 0.001%

    No Known Activations