© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95661
    Prev
    Next
    INDEX
    Explanations

    names of characters and people associated with specific narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ients
    -0.07
     обоÑĢ
    -0.07
     vit
    -0.07
    urse
    -0.06
    foundland
    -0.06
    ala
    -0.06
    ãĤ«ãĥ¼
    -0.06
    UILTIN
    -0.06
    ovie
    -0.06
     Forg
    -0.06
    POSITIVE LOGITS
    rnek
    0.07
    ereal
    0.07
    hare
    0.06
    ximity
    0.06
    reator
    0.06
    ravel
    0.06
    arie
    0.06
    å¯Ł
    0.06
    deaux
    0.06
    encil
    0.06
    Activations Density 0.001%

    No Known Activations