© 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. 40757
    Prev
    Next
    INDEX
    Explanations

    terms related to the issuance of formal documents or reports

    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
    kol
    -0.06
    à¯įà®
    -0.06
    /from
    -0.06
    imensional
    -0.06
    /high
    -0.06
    shire
    -0.06
    nic
    -0.06
    ëĭ¤ê³ł
    -0.06
     ger
    -0.06
    istan
    -0.06
    POSITIVE LOGITS
    acman
    0.07
    redient
    0.07
     noreferrer
    0.07
    rength
    0.07
     forth
    0.07
    quoi
    0.07
    ance
    0.07
    radu
    0.07
     Lad
    0.07
    и
    0.07
    Activations Density 0.035%

    No Known Activations