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. 100437
    Prev
    Next
    INDEX
    Explanations

    variation

    np_max-act · gemini-2.0-flash

    technical terms related to semiconductor devices and their operational parameters.

    oai_token-act-pair · gpt-4o-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
    _predictions
    -0.07
    .assets
    -0.07
     knowledgeable
    -0.06
    .video
    -0.06
    Loads
    -0.06
    Сам
    -0.06
     슬
    -0.06
    LENGTH
    -0.06
     grandparents
    -0.06
     должна
    -0.06
    POSITIVE LOGITS
     هفته
    0.07
     Zimbabwe
    0.07
    -row
    0.06
    .vol
    0.06
    .INTEGER
    0.06
    ensemble
    0.06
    .country
    0.06
    535
    0.06
     xmlns
    0.06
    798
    0.06
    Activations Density 0.022%

    No Known Activations