© 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. 30546
    Prev
    Next
    INDEX
    Explanations

    references to scripts and filmmaking concepts

    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
    457
    -0.07
    ä¹Ļ
    -0.07
    lı
    -0.07
    bject
    -0.07
     ven
    -0.07
    ÙĩÙĩ
    -0.07
    ÑĥÑĢн
    -0.07
    ÑĢиÑĦ
    -0.07
     clin
    -0.06
    948
    -0.06
    POSITIVE LOGITS
    onde
    0.06
    eniable
    0.06
    оÑĪ
    0.06
    ruk
    0.06
    imal
    0.06
    mates
    0.06
    SBATCH
    0.06
    =""/>↵
    0.06
    mate
    0.06
    ülük
    0.06
    Activations Density 0.001%

    No Known Activations