© 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. 93277
    Prev
    Next
    INDEX
    Explanations

    terms related to impending challenges or transitions

    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
    izable
    -0.07
    ongan
    -0.07
    ÑĤÑĮ
    -0.07
    agan
    -0.07
     zal
    -0.06
    eza
    -0.06
     вов
    -0.06
    vit
    -0.06
     Pie
    -0.06
    een
    -0.06
    POSITIVE LOGITS
    /ext
    0.08
    prec
    0.08
    /end
    0.08
     verge
    0.07
     vá»±c
    0.07
     conv
    0.07
    _CONV
    0.07
    .gridView
    0.07
    agnost
    0.07
    icontrol
    0.07
    Activations Density 0.005%

    No Known Activations