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. 75033
    Prev
    Next
    INDEX
    Explanations

    Negative sentiment

    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
    .longitude
    -0.07
    (Page
    -0.07
    Unsupported
    -0.07
    afone
    -0.07
     manufactured
    -0.07
     Lumia
    -0.07
    .Collections
    -0.07
    (each
    -0.07
     زاد
    -0.06
    …↵↵↵↵
    -0.06
    POSITIVE LOGITS
    غات
    0.06
     sc
    0.06
     HOR
    0.06
     Jerseys
    0.06
    vfs
    0.06
     Shame
    0.06
     role
    0.05
    onyms
    0.05
     Game
    0.05
     shame
    0.05
    Activations Density 0.008%

    No Known Activations