© 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. 92211
    Prev
    Next
    INDEX
    Explanations

    references to tangible data or evidence

    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
    659
    -0.07
    978
    -0.06
     explo
    -0.06
    628
    -0.06
     Khal
    -0.06
     society
    -0.06
     fucked
    -0.06
     picture
    -0.06
    847
    -0.06
     Howe
    -0.06
    POSITIVE LOGITS
    afil
    0.08
    avigator
    0.08
    //{{
    0.08
    .epoch
    0.07
    frauen
    0.07
    orta
    0.07
    lemn
    0.07
     веÑĢеÑģ
    0.07
    obox
    0.07
     Dear
    0.07
    Activations Density 0.000%

    No Known Activations