© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25929
    Prev
    Next
    INDEX
    Explanations

    User generated text

    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
     seed
    -0.07
     sneakers
    -0.07
    push
    -0.07
    靠
    -0.06
     fellowship
    -0.06
     Federation
    -0.06
     Feld
    -0.06
     clothes
    -0.06
    ornings
    -0.06
     /*
    -0.06
    POSITIVE LOGITS
     Duration
    0.06
    imilar
    0.06
    opol
    0.06
    .ic
    0.06
    .General
    0.06
    arov
    0.06
    	die
    0.06
    /problem
    0.06
     zkušen
    0.06
    exact
    0.06
    Activations Density 0.145%

    No Known Activations