© 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. 28363
    Prev
    Next
    INDEX
    Explanations

    r

    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
    zer
    -0.08
    period
    -0.07
    eth
    -0.07
    	min
    -0.07
     cms
    -0.06
     Capital
    -0.06
    _contract
    -0.06
    شان
    -0.06
    licant
    -0.06
     Race
    -0.06
    POSITIVE LOGITS
    ありがとう
    0.07
    يانة
    0.07
    getActiveSheet
    0.06
     iCloud
    0.06
    _INS
    0.06
     πιο
    0.06
     πριν
    0.06
    žený
    0.06
    @implementation
    0.06
    _SHA
    0.06
    Activations Density 0.014%

    No Known Activations