© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44428
    Prev
    Next
    INDEX
    Explanations

    consider, evaluate

    np_max-act · gemini-2.0-flash

    This neuron does not activate on any tokens—it effectively detects nothing.

    oai_token-act-pair · o4-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
    grunt
    -0.07
     Active
    -0.06
    ]->
    -0.06
    aced
    -0.06
    	number
    -0.06
    jí
    -0.06
    Ip
    -0.06
     nebude
    -0.06
    nya
    -0.06
    чаются
    -0.06
    POSITIVE LOGITS
    UIL
    0.07
    Aside
    0.06
     Disp
    0.06
     Investig
    0.06
     perplex
    0.06
    _mail
    0.06
    :before
    0.06
    λοι
    0.06
    ($)
    0.06
     س
    0.06
    Activations Density 0.034%

    No Known Activations