© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 125920
    Prev
    Next
    INDEX
    Explanations

    references to notable figures and concepts in literature and film

    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
     ç¶
    -0.07
     naš
    -0.06
    ductive
    -0.06
    iros
    -0.06
    untime
    -0.06
    alcon
    -0.06
    ĨĴ
    -0.06
    à¹Ģà¸ļ
    -0.06
    ÏĦε
    -0.06
    ija
    -0.06
    POSITIVE LOGITS
    orem
    0.08
    indh
    0.07
    awe
    0.06
    olle
    0.06
    959
    0.06
    esch
    0.06
    isol
    0.06
    itle
    0.06
    icher
    0.06
     Lol
    0.06
    Activations Density 0.026%

    No Known Activations