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. 77638
    Prev
    Next
    INDEX
    Explanations

    stadiums

    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
     betrayed
    -0.07
     songs
    -0.07
     But
    -0.07
    _SS
    -0.07
    _yaml
    -0.07
     Beat
    -0.07
     Jill
    -0.06
    indered
    -0.06
     WTF
    -0.06
     seja
    -0.06
    POSITIVE LOGITS
     vyu
    0.07
    几个
    0.06
     Вона
    0.06
     нав
    0.06
    icot
    0.06
     picturesque
    0.06
    ROP
    0.06
     dostate
    0.06
     sofa
    0.06
     synd
    0.06
    Activations Density 0.024%

    No Known Activations