© 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. 83917
    Prev
    Next
    INDEX
    Explanations

    instances of the word "described" in the text

    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
    Logic
    -0.07
    _tolerance
    -0.06
    heck
    -0.06
    ç½²
    -0.06
     NAT
    -0.06
     spin
    -0.06
    uin
    -0.06
     Mos
    -0.06
    ounds
    -0.06
    isas
    -0.06
    POSITIVE LOGITS
    $MESS
    0.08
     kle
    0.07
    اÙĪÛĮ
    0.06
    versions
    0.06
    orer
    0.06
    zi
    0.06
    ัà¸ĩส
    0.06
    'gc
    0.06
    _sibling
    0.06
    ¤
    0.05
    Activations Density 0.000%

    No Known Activations