© 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. 17-LLAMASCOPE-RES-131K
    6. 128533
    Prev
    Next
    INDEX
    Explanations

    elements related to client communication and engagement through newsletters

    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
     Bing
    -0.06
     dual
    -0.06
     du
    -0.06
    ênh
    -0.06
    .arg
    -0.06
    rex
    -0.06
     CSR
    -0.06
    ingle
    -0.05
    CSR
    -0.05
     cot
    -0.05
    POSITIVE LOGITS
     updates
    0.08
    updates
    0.08
    chwitz
    0.07
    ezier
    0.07
    isd
    0.07
     update
    0.07
    ibu
    0.07
     Tits
    0.07
    frequency
    0.07
    divider
    0.07
    Activations Density 0.010%

    No Known Activations