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. 15-RESID-POST-AA
    6. 110621
    Prev
    Next
    INDEX
    Explanations

    qa

    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
    ▍▍▍▍▍▍▍▍
    -0.07
     прох
    -0.06
     Construct
    -0.06
    ิจ
    -0.06
    ')↵↵↵↵
    -0.06
     öğ
    -0.06
     Berlin
    -0.06
     /><
    -0.06
    ّد
    -0.06
    _K
    -0.06
    POSITIVE LOGITS
     succesfully
    0.08
     alert
    0.07
    administrator
    0.07
     freelancer
    0.07
    JSONException
    0.07
    CHEMY
    0.06
    .Execute
    0.06
     BASIS
    0.06
    _bel
    0.06
    getQuery
    0.06
    Activations Density 0.001%

    No Known Activations