© 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. 106030
    Prev
    Next
    INDEX
    Explanations

    adverbs and descriptors that enhance or clarify statements

    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
    ÏĢÏĮ
    -0.07
    inho
    -0.07
    ksen
    -0.07
    iri
    -0.07
    _SHA
    -0.07
    idd
    -0.07
    inning
    -0.06
    kap
    -0.06
    ãĥĪãĥª
    -0.06
    ippers
    -0.06
    POSITIVE LOGITS
     quite
    0.11
    quite
    0.08
    TTY
    0.08
     actually
    0.07
    orney
    0.07
    $MESS
    0.07
     surprisingly
    0.07
     bastante
    0.07
    ãĤ¸ãĤ¢
    0.07
    _abort
    0.07
    Activations Density 0.019%

    No Known Activations