© 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. 118929
    Prev
    Next
    INDEX
    Explanations

    statements about requirements and trends in the digital environment

    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
     genuine
    -0.06
    ç¯ĩ
    -0.06
     prima
    -0.06
    oucher
    -0.06
    icensed
    -0.06
    ENO
    -0.05
     Kam
    -0.05
     wind
    -0.05
    ickle
    -0.05
     sustain
    -0.05
    POSITIVE LOGITS
     increasingly
    0.08
    igr
    0.08
    uples
    0.08
     Trends
    0.07
     kred
    0.07
     yyyy
    0.07
    aira
    0.07
    /Branch
    0.07
     uy
    0.07
    æĻĤ代
    0.07
    Activations Density 0.013%

    No Known Activations