© 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. 15-LLAMASCOPE-RES-131K
    11. 61930
    Prev
    Next
    INDEX
    Explanations

    references to organizations and roles related to community activities and initiatives

    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
    ap
    -0.05
    a
    -0.05
     chosen
    -0.05
    âĢ¦↵
    -0.05
     Glow
    -0.05
    u
    -0.05
    othy
    -0.05
    be
    -0.05
     Nur
    -0.05
     selected
    -0.05
    POSITIVE LOGITS
    /Dk
    0.08
    ç¼ĺ
    0.08
    £i
    0.08
    xae
    0.07
    ghi
    0.07
    iamond
    0.07
    stial
    0.07
    Equip
    0.07
    격
    0.07
    Ľi
    0.07
    Activations Density 0.564%

    No Known Activations