© 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. 71085
    Prev
    Next
    INDEX
    Explanations

    references to programming model definitions and data structure annotations

    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
    borough
    -0.07
    ogen
    -0.07
    land
    -0.07
    ibu
    -0.06
    974
    -0.06
    ism
    -0.06
    ãĤĤãģĹ
    -0.06
    ñ
    -0.06
    ore
    -0.05
    sta
    -0.05
    POSITIVE LOGITS
    aoke
    0.08
    маз
    0.07
    éĤ¦
    0.07
    IFEST
    0.07
    -fontawesome
    0.07
    imde
    0.07
    MouseButton
    0.07
    iad
    0.07
    kem
    0.07
    yne
    0.07
    Activations Density 0.008%

    No Known Activations