© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 35510
    Prev
    Next
    INDEX
    Explanations

    .lang

    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
     yellow
    -0.06
    meler
    -0.06
    elmet
    -0.06
     assertNotNull
    -0.06
     wet
    -0.06
     zlat
    -0.06
    _WRAPPER
    -0.06
    aeper
    -0.06
     deset
    -0.06
    چی
    -0.05
    POSITIVE LOGITS
     Patent
    0.08
     declining
    0.07
     tas
    0.07
    .Section
    0.07
    236
    0.07
    タル
    0.07
    FAILURE
    0.06
    Contained
    0.06
     frauen
    0.06
     Inc
    0.06
    Activations Density 0.000%

    No Known Activations