© 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. 23-RESID-POST-AA
    11. 105090
    Prev
    Next
    INDEX
    Explanations

    Numbers in the 870s

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pulse
    -0.07
     Estado
    -0.07
    icie
    -0.07
     konum
    -0.07
    Codigo
    -0.07
     primaries
    -0.06
     Francis
    -0.06
     Cic
    -0.06
     latino
    -0.06
     birey
    -0.06
    POSITIVE LOGITS
    874
    0.07
     indifference
    0.07
     derby
    0.07
    865
    0.07
    860
    0.06
    рап
    0.06
    off
    0.06
     WH
    0.06
    removeAttr
    0.06
     borderWidth
    0.06
    Activations Density 0.025%

    No Known Activations