© 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
    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. 110238
    Prev
    Next
    INDEX
    Explanations

    outside

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “outside,” especially in phrases like “outside of…”

    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
     Marcel
    -0.08
     Fer
    -0.06
    货
    -0.06
     要
    -0.06
    次数
    -0.06
    004
    -0.06
    Ro
    -0.06
     Jal
    -0.06
    _IDS
    -0.06
     мощ
    -0.06
    POSITIVE LOGITS
     outside
    0.15
     Outside
    0.14
    outside
    0.12
    Outside
    0.10
    SIDE
    0.08
    orde
    0.08
    indir
    0.08
    stone
    0.07
    unde
    0.07
    signed
    0.07
    Activations Density 0.011%

    No Known Activations