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. 23-RESID-POST-AA
    6. 104774
    Prev
    Next
    INDEX
    Explanations

    describing person's height/weight

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wm
    -0.06
     waypoints
    -0.06
    ustum
    -0.06
    *N
    -0.06
     bande
    -0.06
    ensation
    -0.06
    `:
    -0.06
     võ
    -0.06
    Intersection
    -0.06
    ४
    -0.06
    POSITIVE LOGITS
    鳴
    0.07
    .GetInstance
    0.06
    /chat
    0.06
     تشخیص
    0.06
     примен
    0.06
     مشکل
    0.06
    MemoryWarning
    0.06
    します
    0.06
     Ellis
    0.06
    ritt
    0.06
    Activations Density 0.019%

    No Known Activations