© 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. 110071
    Prev
    Next
    INDEX
    Explanations

    room

    np_max-act · gemini-2.0-flash

    This neuron detects the phrase “room for” (i.e. expressions of there being “room for” something).

    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
    .handler
    -0.07
    Become
    -0.07
     adress
    -0.07
    SERVICE
    -0.07
     вкус
    -0.07
     Valk
    -0.07
    _pwd
    -0.06
     diseases
    -0.06
     zien
    -0.06
    /share
    -0.06
    POSITIVE LOGITS
     accommodate
    0.07
     ADM
    0.07
    rý
    0.06
    072
    0.06
     revolving
    0.06
    utenberg
    0.06
    Seat
    0.06
     accommodating
    0.06
     Rowe
    0.06
    _ROOM
    0.06
    Activations Density 0.009%

    No Known Activations