© 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. 36026
    Prev
    Next
    INDEX
    Explanations

    Code functions

    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
    辞
    -0.06
    _MEMBER
    -0.06
    .getStart
    -0.06
     prevalence
    -0.06
    ahrenheit
    -0.06
     Cha
    -0.06
    Workbook
    -0.06
    骨
    -0.06
     chief
    -0.06
     Jays
    -0.06
    POSITIVE LOGITS
    Ui
    0.07
    lj
    0.06
     fd
    0.06
    [List
    0.06
    /d
    0.06
    /local
    0.06
    autiful
    0.06
    ние
    0.06
    _step
    0.06
    设备
    0.06
    Activations Density 0.036%

    No Known Activations