© 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. 86919
    Prev
    Next
    INDEX
    Explanations

    recurring phrases and references in technical or descriptive contexts

    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
    ãģĸ
    -0.07
    aris
    -0.07
    太éĥİ
    -0.07
     Nem
    -0.07
    oi
    -0.06
    çµ±
    -0.06
     Buchanan
    -0.06
    quat
    -0.06
    ãĥģãĥ¥
    -0.06
    imir
    -0.06
    POSITIVE LOGITS
     elsewhere
    0.09
     other
    0.08
     altre
    0.07
    Occurrences
    0.07
    .bunifuFlatButton
    0.07
     otras
    0.07
    'autres
    0.07
    egov
    0.07
    åħ¶ä»ĸ
    0.07
     revers
    0.07
    Activations Density 0.036%

    No Known Activations