© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 57390
    Prev
    Next
    INDEX
    Explanations

    Road and vehicle safety

    np_max-act · gemini-2.0-flash

    This neuron detects safety‐ and caution‐related terms, especially in the context of bicycling (e.g. traffic, rules, awareness, safety, riding).

    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
     muh
    -0.07
    涉
    -0.07
     pallet
    -0.06
     singing
    -0.06
     receptive
    -0.06
    .Inv
    -0.06
     interchange
    -0.06
     diner
    -0.06
    ぇ
    -0.06
    };
↵
↵
    -0.06
    POSITIVE LOGITS
    现
    0.06
    )(
    0.06
    add
    0.06
    California
    0.06
    Texas
    0.06
    ISTS
    0.06
    ?action
    0.06
    _EVENT
    0.06
     terrace
    0.06
     fundraising
    0.06
    Activations Density 0.021%

    No Known Activations