© 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. 89996
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to links and titles

    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
    loo
    -0.08
    olk
    -0.07
     Atomic
    -0.07
     atomic
    -0.07
    Atomic
    -0.07
    usters
    -0.07
    anium
    -0.06
    apa
    -0.06
    imb
    -0.06
    oler
    -0.06
    POSITIVE LOGITS
     TED
    0.07
    ellig
    0.06
    rise
    0.06
    gba
    0.06
    elden
    0.06
    à¸Ħรà¸ļ
    0.06
    elsen
    0.06
    FindBy
    0.06
     Crist
    0.06
    opleft
    0.06
    Activations Density 0.002%

    No Known Activations