© 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. 60876
    Prev
    Next
    INDEX
    Explanations

    negative statements or phrases related to capability or ability

    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
    Ãłng
    -0.07
    iller
    -0.07
    rer
    -0.07
    ovÃŃ
    -0.07
    _SHARED
    -0.07
    cheon
    -0.07
    еб
    -0.07
    rade
    -0.06
    rab
    -0.06
    orro
    -0.06
    POSITIVE LOGITS
    éĢ¸
    0.06
    ByKey
    0.06
    елиÑĩ
    0.06
     industri
    0.06
     nomin
    0.05
     deflect
    0.05
     Smithsonian
    0.05
    _redirect
    0.05
    itom
    0.05
     Hawaiian
    0.05
    Activations Density 0.003%

    No Known Activations