© 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. 78634
    Prev
    Next
    INDEX
    Explanations

    concepts related to opportunities and singular experiences

    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
     instead
    -0.06
    icals
    -0.06
    PARSE
    -0.06
    å¡
    -0.06
    instead
    -0.06
     smallest
    -0.06
    antino
    -0.06
     xls
    -0.06
    ç«Ł
    -0.06
     UIBar
    -0.06
    POSITIVE LOGITS
     Opportunity
    0.07
    ÙĦاÙĤ
    0.06
    ces
    0.06
    Sharper
    0.06
    UniqueId
    0.06
    Impossible
    0.06
     opportunity
    0.06
     tun
    0.06
     certain
    0.06
    :frame
    0.06
    Activations Density 0.007%

    No Known Activations