© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4244
    Prev
    Next
    INDEX
    Explanations

    descriptions of technical specifications and their improvements

    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
    920
    -0.06
    960
    -0.06
    plate
    -0.06
    opp
    -0.06
    810
    -0.06
    620
    -0.06
     Duch
    -0.06
    stance
    -0.06
    è©
    -0.06
    Works
    -0.06
    POSITIVE LOGITS
    ubb
    0.07
    aida
    0.06
    eing
    0.06
    ither
    0.06
    ازÛĮ
    0.06
    _PO
    0.06
    Ļ
    0.06
    coli
    0.06
    idot
    0.06
    abar
    0.06
    Activations Density 0.064%

    No Known Activations