© 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. 91536
    Prev
    Next
    INDEX
    Explanations

    Parenthesis, quotes, "is"

    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
    ))))
    -0.07
    Tk
    -0.07
     hemat
    -0.06
    alam
    -0.06
    )})
    -0.06
    fid
    -0.06
     alıp
    -0.06
    三三
    -0.06
     llama
    -0.06
    ayers
    -0.06
    POSITIVE LOGITS
     metadata
    0.07
    gear
    0.07
     detained
    0.06
     complied
    0.06
    (boost
    0.06
    (screen
    0.06
    east
    0.06
     geared
    0.06
    _FILTER
    0.06
    `${
    0.06
    Activations Density 0.027%

    No Known Activations