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. 60514
    Prev
    Next
    INDEX
    Explanations

    be

    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
    (api
    -0.07
     certificates
    -0.07
     alguna
    -0.07
     properties
    -0.07
    HH
    -0.06
    (sd
    -0.06
    reek
    -0.06
     flags
    -0.06
    (en
    -0.06
     Safari
    -0.06
    POSITIVE LOGITS
     Yap
    0.06
     dày
    0.06
    PropertyParams
    0.06
    ProcessEvent
    0.06
    NIEnv
    0.06
     Herbal
    0.06
    蔵
    0.06
     Purdue
    0.06
     postseason
    0.06
     Unreal
    0.06
    Activations Density 0.203%

    No Known Activations