© 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. 119075
    Prev
    Next
    INDEX
    Explanations

    repetitive qualifiers or expressions of affirmation

    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
     sice
    -0.07
    oreach
    -0.07
    avou
    -0.07
    ÑĥзÑĭ
    -0.07
    ilio
    -0.07
    ÑĤин
    -0.06
    aight
    -0.06
    ãĥ¬ãĥ¼
    -0.06
    arem
    -0.06
    terr
    -0.06
    POSITIVE LOGITS
     other
    0.09
     equally
    0.09
     similarly
    0.07
     otras
    0.07
     another
    0.07
     underlying
    0.07
    ä¸Ģæł·
    0.07
     Other
    0.06
     others
    0.06
     followed
    0.06
    Activations Density 0.029%

    No Known Activations