© 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. 40166
    Prev
    Next
    INDEX
    Explanations

    key elements related to storytelling or narrative structure

    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
    ombat
    -0.06
     Milli
    -0.06
    TARGET
    -0.06
    izards
    -0.06
    èĻİ
    -0.06
    hores
    -0.06
    izu
    -0.06
     classics
    -0.06
    rzy
    -0.06
    AuthGuard
    -0.06
    POSITIVE LOGITS
     survival
    0.10
     Survival
    0.09
    оби
    0.07
     Exped
    0.07
    idel
    0.07
     survive
    0.07
    Surv
    0.07
    irl
    0.06
     Vita
    0.06
    ady
    0.06
    Activations Density 0.001%

    No Known Activations