© 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. 97738
    Prev
    Next
    INDEX
    Explanations

    calls to functions or methods in code

    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
    виÑħ
    -0.07
    же
    -0.07
    км
    -0.07
    ónico
    -0.07
    resi
    -0.07
    .strings
    -0.07
    ëł¹
    -0.07
    jezd
    -0.07
     kav
    -0.07
    менÑĤа
    -0.07
    POSITIVE LOGITS
     Twin
    0.06
     tra
    0.06
    amed
    0.06
    aver
    0.05
    isc
    0.05
    ì¡°
    0.05
    ulfilled
    0.05
     dispersed
    0.05
    avo
    0.05
    à¹Ĥà¸Ļ
    0.05
    Activations Density 0.044%

    No Known Activations