© 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. 5-LLAMASCOPE-RES-131K
    11. 126579
    Prev
    Next
    INDEX
    Explanations

    names referenced in the text

    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
    ardo
    -0.07
    ialized
    -0.07
    gnore
    -0.07
    ieu
    -0.07
    zy
    -0.06
    STREAM
    -0.06
    fait
    -0.06
    PTS
    -0.06
    ahan
    -0.06
    loh
    -0.06
    POSITIVE LOGITS
    _totals
    0.06
    essian
    0.06
     tra
    0.06
     Bare
    0.06
    pliers
    0.06
    sku
    0.06
    cls
    0.06
     mest
    0.06
    ho
    0.06
     Cle
    0.05
    Activations Density 0.005%

    No Known Activations