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. 112828
    Prev
    Next
    INDEX
    Explanations

    was

    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
    ins
    -0.08
    Num
    -0.07
    ILITY
    -0.07
    ify
    -0.06
    خم
    -0.06
     protects
    -0.06
    NGC
    -0.06
    m
    -0.06
    teri
    -0.06
    MESS
    -0.06
    POSITIVE LOGITS
     towering
    0.07
     parach
    0.07
     billboard
    0.07
     it
    0.07
     was
    0.06
    _TRANSACTION
    0.06
    _different
    0.06
     Douglas
    0.06
     Sword
    0.06
    _WALL
    0.06
    Activations Density 0.027%

    No Known Activations