© 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. 107664
    Prev
    Next
    INDEX
    Explanations

    high-value real estate properties

    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
    izon
    -0.08
    cestor
    -0.07
    åŃĿ
    -0.07
    //{{
    -0.07
    вÑĥ
    -0.06
    vection
    -0.06
     prec
    -0.06
    cheap
    -0.06
    æ®
    -0.06
    еÑĪ
    -0.06
    POSITIVE LOGITS
     private
    0.08
     Private
    0.07
    private
    0.07
     gated
    0.07
     house
    0.07
    éĹ
    0.07
    ÄĽt
    0.07
    .grpc
    0.07
     exclusive
    0.06
     Rare
    0.06
    Activations Density 0.009%

    No Known Activations