© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 94497
    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
     Storage
    -0.07
    Ta
    -0.06
    archy
    -0.06
    enis
    -0.06
    になって
    -0.06
     tensor
    -0.06
     ilma
    -0.06
    ildo
    -0.06
     INDEX
    -0.06
    _MSG
    -0.06
    POSITIVE LOGITS
    aticon
    0.07
     �
    0.06
     TD
    0.06
    spam
    0.06
    Delegate
    0.06
     Athens
    0.06
    니까
    0.06
     pops
    0.06
     wiel
    0.06
     afl
    0.06
    Activations Density 0.775%

    No Known Activations