© 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. 15-LLAMASCOPE-RES-131K
    11. 103677
    Prev
    Next
    INDEX
    Explanations

    key terms related to notable figures and their backgrounds

    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
    ersen
    -0.08
    rud
    -0.08
    idas
    -0.08
    imensional
    -0.07
    çĽijåIJ¬é¡µéĿ¢
    -0.07
    swick
    -0.07
    tae
    -0.07
    haf
    -0.07
    erson
    -0.07
    Ñģок
    -0.07
    POSITIVE LOGITS
     Arbor
    0.07
    ,strlen
    0.06
     Hollow
    0.06
    ube
    0.06
     '''
    0.06
    ableObject
    0.05
     Brun
    0.05
     ÙħÙĨظÙĪر
    0.05
     "...
    0.05
    UBE
    0.05
    Activations Density 0.000%

    No Known Activations