© 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. 7-RESID-POST-AA
    11. 97820
    Prev
    Next
    INDEX
    Explanations

    (null

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dvěma
    -0.07
    UNET
    -0.07
    dot
    -0.06
     appName
    -0.06
     prefs
    -0.06
     BAT
    -0.06
     gusto
    -0.06
    XR
    -0.06
    trag
    -0.06
    _stage
    -0.06
    POSITIVE LOGITS
    (null
    0.10
    (NULL
    0.08
    .documentElement
    0.07
     NULL
    0.06
    (""
    0.06
    :null
    0.06
    (undefined
    0.06
     cin
    0.06
     None
    0.06
    WidgetItem
    0.06
    Activations Density 0.003%

    No Known Activations