© 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. 5-LLAMASCOPE-RES-131K
    11. 126069
    Prev
    Next
    INDEX
    Explanations

    themes related to social justice and individual responsibility

    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
    tright
    -0.06
    tura
    -0.06
    ispers
    -0.06
    ighth
    -0.06
    εÏĤ
    -0.06
     Pal
    -0.06
    gis
    -0.06
    incare
    -0.06
    ohana
    -0.06
    ulur
    -0.06
    POSITIVE LOGITS
    CLS
    0.07
     propor
    0.07
    .rl
    0.06
    Це
    0.06
    anto
    0.06
    à¸ģรรม
    0.06
     menn
    0.06
    edin
    0.06
    رÙģ
    0.06
     ëĵ
    0.06
    Activations Density 0.026%

    No Known Activations