© 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. 55907
    Prev
    Next
    INDEX
    Explanations

    references to simulation processes and related concepts

    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
    itel
    -0.07
    нак
    -0.07
    sword
    -0.07
    eenth
    -0.07
    à¸ģำ
    -0.07
    age
    -0.07
    ened
    -0.07
    heid
    -0.07
    ÑģÑı
    -0.06
    ese
    -0.06
    POSITIVE LOGITS
    ERCHANT
    0.09
    oeff
    0.08
    IRROR
    0.08
    clair
    0.08
    aneously
    0.08
    posium
    0.07
    EDIUM
    0.07
    ulators
    0.07
    abant
    0.07
    atic
    0.07
    Activations Density 0.024%

    No Known Activations