© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75153
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negative outcomes or conclusions

    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
    celik
    -0.08
    ysa
    -0.08
     spender
    -0.08
    .appspot
    -0.07
    inkle
    -0.07
     neod
    -0.07
    cheme
    -0.07
    µľ
    -0.07
    interop
    -0.07
    esi
    -0.07
    POSITIVE LOGITS
     cul
    0.07
     a
    0.06
     repeat
    0.06
     compromise
    0.06
     Stre
    0.06
     complete
    0.06
     Twe
    0.06
     disaster
    0.06
     either
    0.06
     sel
    0.06
    Activations Density 0.014%

    No Known Activations