© 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. 5406
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    %%
    -0.06
     ="
    -0.06
     envoy
    -0.06
    _measurement
    -0.06
     rightful
    -0.06
     rainfall
    -0.06
    either
    -0.06
    工具
    -0.06
     Pollution
    -0.06
     XL
    -0.06
    POSITIVE LOGITS
    ơm
    0.07
     DAR
    0.07
    __);↵
    0.07
    بع
    0.07
     ofere
    0.07
    ungen
    0.06
    pen
    0.06
    ści
    0.06
    lab
    0.06
    ój
    0.06
    Activations Density 0.064%

    No Known Activations