© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87095
    Prev
    Next
    INDEX
    Explanations

    specific technical or programming terms related to structures and states in code

    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
    ÑĨин
    -0.06
     Kostenlose
    -0.06
    ossa
    -0.06
    uest
    -0.06
    anova
    -0.06
    608
    -0.05
    ä¼°
    -0.05
    wing
    -0.05
    aged
    -0.05
    wor
    -0.05
    POSITIVE LOGITS
    gnore
    0.08
    .UnitTesting
    0.08
    ulfilled
    0.07
    ignKey
    0.07
    ør
    0.07
    naments
    0.07
    ãĥĥãĥĪ
    0.07
    .mixer
    0.07
    imeType
    0.06
    auge
    0.06
    Activations Density 0.291%

    No Known Activations