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. 15-RESID-POST-AA
    6. 24587
    Prev
    Next
    INDEX
    Explanations

    code variables

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     towers
    -0.07
     Chancellor
    -0.06
     Streets
    -0.06
    oref
    -0.06
     Loren
    -0.06
     oranges
    -0.06
     OPS
    -0.06
    producer
    -0.06
    arrison
    -0.06
     Downtown
    -0.06
    POSITIVE LOGITS
    ')
    0.07
    andard
    0.06
    icy
    0.06
    (eval
    0.06
     juste
    0.06
    _QUESTION
    0.06
     cj
    0.06
    �
    0.06
     gitti
    0.06
    RANDOM
    0.06
    Activations Density 0.021%

    No Known Activations