© 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. 9-LLAMASCOPE-RES-131K
    11. 98054
    Prev
    Next
    INDEX
    Explanations

    audio file format types and specifications

    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
     dual
    -0.06
    resh
    -0.06
     Zhu
    -0.06
     Filip
    -0.06
    elo
    -0.06
    plication
    -0.05
    aul
    -0.05
    hu
    -0.05
     Cold
    -0.05
     BÃŃ
    -0.05
    POSITIVE LOGITS
    /GPL
    0.08
    eci
    0.08
    qus
    0.07
    antium
    0.07
    _pri
    0.07
    ove
    0.07
    lemn
    0.07
    anium
    0.07
    loud
    0.07
    $MESS
    0.07
    Activations Density 0.001%

    No Known Activations