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. 55183
    Prev
    Next
    INDEX
    Explanations

    outside

    np_max-act · gemini-2.0-flash

    the intention of a person to hydrate before leaving for a destination.

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

    The neuron chiefly detects mentions of weather conditions (e.g. “snowing,” “raining,” “outside”).

    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
    Git
    -0.06
    spm
    -0.06
    _python
    -0.06
    jualan
    -0.06
     algum
    -0.06
    chemist
    -0.06
     Pill
    -0.06
    operations
    -0.06
     blanket
    -0.06
    violent
    -0.06
    POSITIVE LOGITS
     outside
    0.09
     Outside
    0.08
    ি�
    0.07
     exterior
    0.07
    outside
    0.06
     jsonString
    0.06
     out
    0.06
    Outside
    0.06
     gif
    0.06
    �
    0.06
    Activations Density 0.007%

    No Known Activations