© 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. 126040
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data processing and analysis

    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
     anybody
    -0.08
     ultimately
    -0.07
     anyone
    -0.07
    еÑĤа
    -0.07
    imits
    -0.06
    zych
    -0.06
    ModelProperty
    -0.06
    piar
    -0.06
     noveller
    -0.06
    ervas
    -0.06
    POSITIVE LOGITS
     chances
    0.07
     additional
    0.07
     odds
    0.07
     probably
    0.07
     instead
    0.07
     extra
    0.06
    .additional
    0.06
    additional
    0.06
     ëįĶìļ±
    0.06
    probably
    0.06
    Activations Density 0.088%

    No Known Activations