© 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. 3294
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ample" and its variations

    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
    _RENDERER
    -0.07
    lsen
    -0.07
    绣
    -0.07
    /respond
    -0.07
     eof
    -0.06
    jem
    -0.06
     clen
    -0.06
    swers
    -0.06
    uzzi
    -0.06
    ially
    -0.06
    POSITIVE LOGITS
     opportunity
    0.09
     enough
    0.09
     amount
    0.08
     opportunities
    0.08
    amount
    0.08
     amounts
    0.08
    ossal
    0.07
    zier
    0.07
    ä½Ļ
    0.07
    yi
    0.07
    Activations Density 0.006%

    No Known Activations