© 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. 94876
    Prev
    Next
    INDEX
    Explanations

    references to service endpoints or API calls

    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
    alc
    -0.07
    ret
    -0.06
    suming
    -0.06
    ết
    -0.06
    etti
    -0.06
    dÃŃ
    -0.06
    nie
    -0.06
    ven
    -0.06
    orz
    -0.06
    .getExternal
    -0.06
    POSITIVE LOGITS
    onu
    0.06
    uce
    0.06
    ohana
    0.06
    oulouse
    0.06
    ç²Ĵ
    0.06
    odyn
    0.06
     POD
    0.06
    baugh
    0.06
    anken
    0.06
    kinson
    0.06
    Activations Density 0.000%

    No Known Activations