© 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. 17-LLAMASCOPE-RES-131K
    11. 27799
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and directives, particularly including statements and file paths

    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
    QUIT
    -0.07
    abin
    -0.06
    /temp
    -0.06
    mlin
    -0.06
    agr
    -0.06
    aille
    -0.06
    ãĥ©ãĤ¤
    -0.06
    UILD
    -0.06
    baugh
    -0.06
     Briggs
    -0.06
    POSITIVE LOGITS
    İ·
    0.07
     Mez
    0.07
    ogi
    0.06
    ãĥ£
    0.06
    untime
    0.06
    maxlength
    0.06
    aten
    0.06
     Studies
    0.06
    enberg
    0.06
    asel
    0.06
    Activations Density 0.000%

    No Known Activations