© 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. 40167
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting markers

    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
    enant
    -0.07
    anco
    -0.07
    anyak
    -0.07
    ould
    -0.07
    ãĥªãĤ¢
    -0.07
    ÑģÑĤÑİ
    -0.07
    ãģ®ãģł
    -0.06
    ãĥģãĥ¥
    -0.06
    aurant
    -0.06
    cat
    -0.06
    POSITIVE LOGITS
     Flor
    0.07
     Several
    0.07
    ahren
    0.06
    rlen
    0.06
     several
    0.06
     both
    0.06
     ?↵
    0.06
     Applied
    0.06
    æķ´ä¸ª
    0.06
     Both
    0.06
    Activations Density 0.000%

    No Known Activations