© 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. 3398
    Prev
    Next
    INDEX
    Explanations

    references to testing or validation processes

    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
    unc
    -0.07
    .exc
    -0.06
    UNC
    -0.06
    _OVERRIDE
    -0.06
    avel
    -0.06
    ower
    -0.06
    -validate
    -0.06
    森
    -0.06
    anca
    -0.06
     Tower
    -0.06
    POSITIVE LOGITS
    ä¸Ģä¸ĭ
    0.07
     rằng
    0.07
     bahwa
    0.07
     basic
    0.06
    /basic
    0.06
     against
    0.06
    hof
    0.06
     BASIC
    0.06
     whether
    0.06
    istrovstvÃŃ
    0.06
    Activations Density 0.011%

    No Known Activations