© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 120893
    Prev
    Next
    INDEX
    Explanations

    PowerPoint presentations

    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
     crashes
    -0.07
    .UN
    -0.07
    inho
    -0.06
    /index
    -0.06
     offsetX
    -0.06
    _login
    -0.06
    Australian
    -0.06
    Ingredient
    -0.06
     Santos
    -0.06
     minutes
    -0.06
    POSITIVE LOGITS
    ří
    0.06
    aiser
    0.06
    istor
    0.06
     Siber
    0.06
     prefetch
    0.06
     polys
    0.06
    ležit
    0.06
     Держав
    0.06
     underst
    0.06
    	texture
    0.06
    Activations Density 0.046%

    No Known Activations