© 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. 17-LLAMASCOPE-RES-131K
    11. 76663
    Prev
    Next
    INDEX
    Explanations

    geological time periods and related concepts

    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
    orgt
    -0.06
    orra
    -0.06
    ettel
    -0.06
     Gram
    -0.06
    /read
    -0.06
     bald
    -0.06
    aub
    -0.05
    ฯ
    -0.05
     penet
    -0.05
     Jehovah
    -0.05
    POSITIVE LOGITS
    udit
    0.08
    -begin
    0.07
    -middle
    0.07
    à¸ķà¸Ńà¸Ļ
    0.07
    lando
    0.07
    hone
    0.07
    -upper
    0.06
     Invent
    0.06
    Assert
    0.06
    .extensions
    0.06
    Activations Density 0.003%

    No Known Activations