© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77146
    Prev
    Next
    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash

    products and services related to installation and maintenance in the engineering or industrial sectors.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
     toward
    -0.08
     spill
    -0.07
     Publication
    -0.07
     birth
    -0.07
     Firebase
    -0.07
     publication
    -0.07
     water
    -0.07
     clusters
    -0.07
     knife
    -0.07
     records
    -0.07
    POSITIVE LOGITS
     playing
    0.07
    Play
    0.07
     dalam
    0.07
     ("\
    0.07
     jugar
    0.07
     Play
    0.07
     Obviously
    0.07
    引き
    0.06
    uestas
    0.06
     play
    0.06
    Activations Density 0.026%

    No Known Activations