© 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. 68904
    Prev
    Next
    INDEX
    Explanations

    Document snippets

    np_max-act · gemini-2.0-flash

    information related to theoretical concepts in physics, specifically string theory and its implications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on placeholder tokens for entity names (e.g., “NAME”, “NAME_1”, etc.).

    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
     maduras
    -0.07
    mont
    -0.07
     Schmidt
    -0.07
    ッカー
    -0.06
     ヴ
    -0.06
     Bedford
    -0.06
    .conn
    -0.06
     एड
    -0.06
    Util
    -0.06
    zt
    -0.06
    POSITIVE LOGITS
    ]:=
    0.06
     Nass
    0.06
     cushion
    0.06
     Provision
    0.06
    
    0.06
     PHP
    0.06
    .viewer
    0.06
    บรร
    0.06
     fights
    0.06
     provision
    0.06
    Activations Density 0.033%

    No Known Activations