Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 123556
    Prev
    Next
    INDEX
    Explanations

    code/errors

    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
     commencement
    -0.06
    /cmd
    -0.06
    encent
    -0.06
    .Lock
    -0.06
     يع
    -0.06
     scalability
    -0.06
     Ре
    -0.06
    ガ
    -0.06
     बल
    -0.06
    ATTR
    -0.06
    POSITIVE LOGITS
    _DX
    0.07
                        
    ↵
    0.06
    进
    0.06
    InProgress
    0.06
    SOC
    0.06
     фор
    0.06
    Interested
    0.06
    %%%%%%%%%%%%%%%%
    0.06
     cum
    0.06
     ped
    0.06
    Activations Density 0.079%

    No Known Activations