Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 106535
    Prev
    Next
    INDEX
    Explanations

    specific chemical compounds or substances

    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
    rete
    -0.06
    ntl
    -0.06
     extr
    -0.06
    ril
    -0.06
    krom
    -0.06
    inte
    -0.06
    viso
    -0.06
    ostel
    -0.06
    uchen
    -0.06
    raf
    -0.06
    POSITIVE LOGITS
    'gc
    0.07
    ahoma
    0.07
    ae
    0.07
    inae
    0.07
    unda
    0.07
    šov
    0.06
    IBUTES
    0.06
    ensen
    0.06
    urus
    0.06
    ector
    0.06
    Activations Density 0.000%

    No Known Activations