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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106094
    Prev
    Next
    INDEX
    Explanations

    elements related to documentation and resources, including links, measurements, errors, and file representations

    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
    enez
    -0.07
    ustral
    -0.07
     Rig
    -0.07
    ç¯
    -0.06
    wer
    -0.06
    zz
    -0.06
    owitz
    -0.06
     Canter
    -0.06
    (crate
    -0.06
    okin
    -0.06
    POSITIVE LOGITS
    tember
    0.08
    .xhtml
    0.08
    CSI
    0.07
    beck
    0.07
    inha
    0.07
    æĥij
    0.07
    à§į
    0.07
    Å¡il
    0.07
    dbus
    0.07
    ÃĵN
    0.07
    Activations Density 0.030%

    No Known Activations