© 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. 125408
    Prev
    Next
    INDEX
    Explanations

    negative or uncertain expressions

    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
    á»ijt
    -0.08
    缮åīį
    -0.07
     currently
    -0.07
    loy
    -0.07
    loyd
    -0.07
    recent
    -0.07
    chw
    -0.07
     unchanged
    -0.07
     recent
    -0.07
     current
    -0.07
    POSITIVE LOGITS
     anything
    0.08
    anything
    0.07
    [Index
    0.07
     viel
    0.07
     anybody
    0.07
     much
    0.07
    ä»»ä½ķ
    0.06
    much
    0.06
     publicly
    0.06
    ystore
    0.06
    Activations Density 0.028%

    No Known Activations