© 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. 11-RESID-POST-AA
    11. 100033
    Prev
    Next
    INDEX
    Explanations

    test

    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_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
    련
    -0.07
    ius
    -0.07
    umpt
    -0.07
     Parallel
    -0.07
    .OR
    -0.06
    ables
    -0.06
     Obr
    -0.06
    Port
    -0.06
     Tutorial
    -0.06
    omez
    -0.06
    POSITIVE LOGITS
     GetLastError
    0.07
    ře
    0.06
     berhasil
    0.06
    @endforeach
    0.06
    DetailView
    0.06
     cargar
    0.06
    .dst
    0.06
    @Data
    0.06
    (bean
    0.06
     sotto
    0.06
    Activations Density 0.002%

    No Known Activations