© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61885
    Prev
    Next
    INDEX
    Explanations

    references to specific places or organizations, particularly related to institutions or formal entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    It detects informative, expository/encyclopedic tokens — words that appear in factual descriptions, specifications, or technical/descriptive passages.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idor
    -0.08
    AINED
    -0.07
    addle
    -0.07
    FontAwesome
    -0.07
    dera
    -0.06
    qing
    -0.06
    nt
    -0.06
    linger
    -0.06
     Perkins
    -0.06
     undert
    -0.06
    POSITIVE LOGITS
     SOCK
    0.07
    ondere
    0.07
    quot
    0.07
    isque
    0.06
    azu
    0.06
     Sak
    0.06
    olen
    0.06
    Ãł
    0.06
    ÑĥÑĢÑĭ
    0.06
    olec
    0.06
    Activations Density 0.787%

    No Known Activations