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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 25478
    Prev
    Next
    INDEX
    Explanations

    Looking for signs

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Pop
    -0.07
    SHA
    -0.07
     Legs
    -0.07
    xes
    -0.06
     Sha
    -0.06
     Powder
    -0.06
    vals
    -0.06
     homework
    -0.06
     wxDefault
    -0.06
    	boost
    -0.06
    POSITIVE LOGITS
    �
    0.07
    <|python_tag|>
    0.06
     rom
    0.06
    olución
    0.06
    arrings
    0.06
    чие
    0.06
    PI
    0.06
    romo
    0.06
    ранения
    0.06
    uetype
    0.06
    Activations Density 0.029%

    No Known Activations