© 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. 17-LLAMASCOPE-RES-131K
    11. 30607
    Prev
    Next
    INDEX
    Explanations

    phrases that reference "first time" or initial occurrences

    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
    ater
    -0.07
    ä¸Ī
    -0.07
    ãĤıãģļ
    -0.06
    ãģªãģĹ
    -0.06
    peria
    -0.06
    opause
    -0.06
    737
    -0.06
    969
    -0.06
    à¥ĭह
    -0.06
    .Σ
    -0.06
    POSITIVE LOGITS
    unately
    0.07
    ãģ®åŃIJ
    0.07
    enco
    0.07
    AFX
    0.07
    abbit
    0.07
    èĤ²
    0.07
    alker
    0.07
    381
    0.07
    InstanceState
    0.06
    indre
    0.06
    Activations Density 0.004%

    No Known Activations