© 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. 9-LLAMASCOPE-RES-131K
    11. 96597
    Prev
    Next
    INDEX
    Explanations

    sections and headings that indicate study methodology and background information

    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
    pear
    -0.06
    IDA
    -0.06
    ida
    -0.06
    471
    -0.06
    ax
    -0.05
    oga
    -0.05
    ci
    -0.05
    itable
    -0.05
    574
    -0.05
     Flam
    -0.05
    POSITIVE LOGITS
    oland
    0.09
    ãĥĥãĤ·ãĥ¥
    0.07
    ifix
    0.07
    letcher
    0.07
    _UNLOCK
    0.07
    iali
    0.06
    /preferences
    0.06
    .metamodel
    0.06
     tongues
    0.06
    rane
    0.06
    Activations Density 0.003%

    No Known Activations