© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103570
    Prev
    Next
    INDEX
    Explanations

    references to creative concepts and productions

    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
    ameleon
    -0.06
    olumn
    -0.06
    achel
    -0.06
    onga
    -0.06
    chsel
    -0.06
    orias
    -0.06
    illac
    -0.06
    ανα
    -0.06
     configFile
    -0.06
    .='
    -0.06
    POSITIVE LOGITS
     Bilg
    0.07
    idea
    0.07
    otel
    0.07
    _GENERIC
    0.07
     idea
    0.06
    opl
    0.06
    ushing
    0.06
     production
    0.06
     Idea
    0.06
    .GetChild
    0.06
    Activations Density 0.004%

    No Known Activations