© 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. 17-LLAMASCOPE-RES-131K
    11. 76331
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and titles associated with significant individuals and works in the documentary field

    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
    ader
    -0.07
    gang
    -0.07
    cation
    -0.07
    -react
    -0.07
    lesh
    -0.07
    arov
    -0.06
     ciz
    -0.06
     Bernstein
    -0.06
    ided
    -0.06
    OOD
    -0.06
    POSITIVE LOGITS
    ardon
    0.09
    naissance
    0.08
    agle
    0.07
    resher
    0.07
    entrant
    0.07
    issance
    0.07
    linger
    0.07
    ults
    0.07
    istance
    0.07
    cep
    0.07
    Activations Density 0.023%

    No Known Activations