© 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. 95541
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods or events

    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
    arehouse
    -0.08
    øj
    -0.07
    æĤ
    -0.07
    ken
    -0.07
     Weeks
    -0.06
    datable
    -0.06
    Lifetime
    -0.06
    izo
    -0.06
     Spells
    -0.06
    .EventArgs
    -0.06
    POSITIVE LOGITS
    ï¸
    0.06
    pid
    0.06
    ity
    0.06
    orny
    0.06
    ERNEL
    0.06
     begin
    0.06
    zza
    0.06
    orem
    0.06
    744
    0.06
    apes
    0.05
    Activations Density 0.072%

    No Known Activations