Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 85707
    Prev
    Next
    INDEX
    Explanations

    Font size

    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
     dày
    -0.07
    ربه
    -0.06
    longitude
    -0.06
     đòi
    -0.06
     Olymp
    -0.06
     ring
    -0.06
    _OBS
    -0.06
     Heavy
    -0.06
     ihtiyac
    -0.06
     Çağ
    -0.06
    POSITIVE LOGITS
    ِّ
    0.07
    віль
    0.07
    autoreleasepool
    0.06
    ″
    0.06
     movers
    0.06
    ΟΛΟΓ
    0.06
    Here
    0.06
    анія
    0.06
    .Cookies
    0.06
    tres
    0.06
    Activations Density 0.017%

    No Known Activations