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. 42068
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    actions and descriptions related to authority and submission dynamics.

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

    This neuron appears to be inactive and does not detect or respond to any specific token or pattern.

    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
    INST
    -0.06
     HW
    -0.06
    .Components
    -0.06
    prm
    -0.06
    ��
    -0.06
    els
    -0.06
    Jer
    -0.06
     SOCKET
    -0.05
    .An
    -0.05
     NodeList
    -0.05
    POSITIVE LOGITS
     @$_
    0.07
     mú
    0.06
     actresses
    0.06
    /*/
    0.06
     mirac
    0.06
    .bot
    0.06
     Kylie
    0.06
    deliver
    0.06
    >');↵↵
    0.06
     Bravo
    0.06
    Activations Density 0.105%

    No Known Activations