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. 1470
    Prev
    Next
    INDEX
    Explanations

    actions

    np_max-act · gemini-2.0-flash

    The neuron detects past-tense verbs (verbs indicating completed actions).

    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
     Mitgli
    -0.07
     []);↵↵
    -0.06
    ジア
    -0.06
    ος
    -0.06
    _Code
    -0.06
    .Run
    -0.06
     hdc
    -0.06
    gc
    -0.06
     ga
    -0.06
    /test
    -0.05
    POSITIVE LOGITS
    ercicio
    0.07
    (library
    0.07
    (['
    0.07
     trader
    0.07
     put
    0.06
     दब
    0.06
     ความ
    0.06
    nel
    0.06
     Kron
    0.06
     sæ
    0.06
    Activations Density 0.109%

    No Known Activations