© 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. 8976
    Prev
    Next
    INDEX
    Explanations

    Hibernation, dormancy

    np_max-act · gemini-2.0-flash

    The neuron activates on terms referring to animal dormancy states, especially words like “hibernation” or “dormancy.”

    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
    ैट
    -0.07
    .observe
    -0.07
    Jones
    -0.06
    owell
    -0.06
    mlink
    -0.06
     Briggs
    -0.06
     DEST
    -0.06
    投資
    -0.06
     pillow
    -0.06
     قبل
    -0.06
    POSITIVE LOGITS
     fools
    0.08
     conven
    0.07
    (project
    0.06
     }));↵
    0.06
     christ
    0.06
     saturn
    0.06
     complexion
    0.06
     super
    0.06
     HDC
    0.06
    Govern
    0.06
    Activations Density 0.007%

    No Known Activations