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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-LLAMASCOPE-RES-131K
    6. 5736
    Prev
    Next
    INDEX
    Explanations

    programming-related questions and errors

    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
    Towards
    -0.07
    Cheers
    -0.06
     Cheers
    -0.06
     Towards
    -0.06
    oogle
    -0.06
    ikki
    -0.06
    Attempting
    -0.06
    éĺµ
    -0.06
    idebar
    -0.06
     ourselves
    -0.06
    POSITIVE LOGITS
    actually
    0.09
     please
    0.08
     actually
    0.08
    please
    0.08
     Actually
    0.08
     anybody
    0.07
    uja
    0.07
    请
    0.07
     somebody
    0.07
    .infinity
    0.07
    Activations Density 0.023%

    No Known Activations