© 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. 28824
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating the end of sentences or clauses

    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
    kili
    -0.08
    otas
    -0.07
    oot
    -0.07
     Grip
    -0.07
    nts
    -0.06
    rez
    -0.06
    isman
    -0.06
    ÃŃk
    -0.06
    اث
    -0.06
     Moss
    -0.06
    POSITIVE LOGITS
     generally
    0.09
     Generally
    0.08
     Suff
    0.08
    Generally
    0.07
     typically
    0.07
    gener
    0.07
     Jae
    0.07
    typically
    0.07
     Typically
    0.07
    quent
    0.07
    Activations Density 0.029%

    No Known Activations