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. 11-RESID-POST-AA
    6. 99409
    Prev
    Next
    INDEX
    Explanations

    ulation

    np_max-act · gemini-2.0-flash

    legal terms and phrases related to court cases and decisions.

    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
     membranes
    -0.07
    .mapping
    -0.07
    Accent
    -0.07
     olab
    -0.07
    Ascii
    -0.07
     invitations
    -0.06
    _EX
    -0.06
     shattered
    -0.06
     retrieval
    -0.06
     beam
    -0.06
    POSITIVE LOGITS
     Sporting
    0.08
     Owned
    0.07
    rique
    0.07
    ambre
    0.06
    -owned
    0.06
     San
    0.06
    vas
    0.06
    .CustomButton
    0.06
    ITIONAL
    0.06
     guar
    0.06
    Activations Density 0.001%

    No Known Activations