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. 22097
    Prev
    Next
    INDEX
    Explanations

    legal context

    np_max-act · gemini-2.0-flash

    documents related to veterans' appeals for disability benefits.

    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
     edge
    -0.06
     sang
    -0.06
    류
    -0.06
    .Not
    -0.06
    ”的
    -0.06
    Hello
    -0.06
     яка
    -0.06
     demonstrating
    -0.06
    _j
    -0.06
    da
    -0.06
    POSITIVE LOGITS
     ApplicationDbContext
    0.08
     UIAlertAction
    0.07
     bindActionCreators
    0.07
    大
    0.07
     FetchType
    0.07
    _GRP
    0.06
    /comments
    0.06
    readcrumbs
    0.06
    getClass
    0.06
    actical
    0.06
    Activations Density 0.004%

    No Known Activations