Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 84692
    Prev
    Next
    INDEX
    Explanations

    immediate/direct

    np_max-act · gemini-2.0-flash

    The neuron detects descriptive phrases detailing a character’s immediate surroundings or environment.

    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
    しかし
    -0.07
     peasants
    -0.06
    terror
    -0.06
    :return
    -0.06
     Matrix
    -0.06
     uniqu
    -0.06
    rev
    -0.06
    �
    -0.06
     jclass
    -0.06
     Borrow
    -0.06
    POSITIVE LOGITS
    genre
    0.07
    hir
    0.07
    اهی
    0.06
    (SE
    0.06
     GitHub
    0.06
     boundaries
    0.06
    	pm
    0.06
    authorization
    0.06
     secretion
    0.06
    σιμοποι
    0.06
    Activations Density 0.001%

    No Known Activations