© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16155
    Prev
    Next
    INDEX
    Explanations

    details about player actions and game 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
     Ops
    -0.07
    QualifiedName
    -0.07
     ìĽĶìĦ¸
    -0.07
    ån
    -0.07
    ancial
    -0.07
    fulWidget
    -0.07
    .AR
    -0.07
    fram
    -0.07
    ä¸ļ
    -0.07
    ÙĪÙĦات
    -0.07
    POSITIVE LOGITS
     vs
    0.08
     versus
    0.07
     tonight
    0.07
     Vs
    0.07
    _vs
    0.07
     against
    0.07
    eron
    0.06
    é£
    0.06
    amac
    0.06
     tomorrow
    0.06
    Activations Density 0.005%

    No Known Activations