© 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. 54630
    Prev
    Next
    INDEX
    Explanations

    references to specific cases or instances

    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
    asto
    -0.07
    ep
    -0.06
    sv
    -0.06
    ilim
    -0.06
    irk
    -0.06
    ipop
    -0.06
    аÑİ
    -0.06
    rend
    -0.06
    isman
    -0.06
     davon
    -0.06
    POSITIVE LOGITS
    case
    0.09
    cases
    0.09
    -case
    0.08
     case
    0.08
     Case
    0.08
    .case
    0.07
    Case
    0.07
    åł´åIJĪãģ¯
    0.07
    azo
    0.07
    ÙĪتÛĮ
    0.07
    Activations Density 0.005%

    No Known Activations