© 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. 22-LLAMASCOPE-RES-131K
    11. 4306
    Prev
    Next
    INDEX
    Explanations

    references to official meetings and council activities

    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
    anian
    -0.07
    yne
    -0.07
    zes
    -0.06
     roÄįnÃŃ
    -0.06
    oki
    -0.06
    ucs
    -0.06
    Ìģc
    -0.06
    chap
    -0.06
     chap
    -0.06
    abis
    -0.06
    POSITIVE LOGITS
     dated
    0.10
    dated
    0.08
     held
    0.08
    held
    0.08
    tern
    0.07
    qu
    0.07
     Buckley
    0.07
    izard
    0.06
    attro
    0.06
    ald
    0.06
    Activations Density 0.006%

    No Known Activations