Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96014
    Prev
    Next
    INDEX
    Explanations

    file path references

    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
    s
    -0.11
     likes
    -0.07
    amma
    -0.07
    ÏĤ
    -0.07
    edio
    -0.06
    ource
    -0.06
     gel
    -0.06
    chw
    -0.06
     gap
    -0.06
    sans
    -0.06
    POSITIVE LOGITS
    itesse
    0.07
    akin
    0.07
    _,,
    0.07
    -webpack
    0.06
       
    0.06
    lak
    0.06
     sứ
    0.06
     Snyder
    0.06
    nyder
    0.06
    /jav
    0.06
    Activations Density 0.008%

    No Known Activations