© 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 EvalsExportsAPI 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. 77304
    Prev
    Next
    INDEX
    Explanations

    quotations or references to written works

    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
    .scalablytyped
    -0.09
    alles
    -0.07
     mapStateToProps
    -0.07
    rana
    -0.07
    kou
    -0.06
    ippers
    -0.06
    ngr
    -0.06
    annon
    -0.06
    ngrx
    -0.06
    gil
    -0.06
    POSITIVE LOGITS
    ìĥģìľĦ
    0.06
     Daw
    0.06
    unta
    0.06
     Starr
    0.06
    ãĥ¥
    0.06
    ç§ĭ
    0.06
     pil
    0.06
     rico
    0.06
    restart
    0.06
    ep
    0.06
    Activations Density 0.004%

    No Known Activations