© 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. 79718
    Prev
    Next
    INDEX
    Explanations

    references to publication details and citation formats

    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
    Indented
    -0.07
    eness
    -0.07
    bew
    -0.07
    -buffer
    -0.07
    ãĥ¼ãĥł
    -0.07
    owan
    -0.07
    itness
    -0.07
    .stamp
    -0.07
    _iff
    -0.06
    utar
    -0.06
    POSITIVE LOGITS
    ượng
    0.06
    anzi
    0.06
    ilm
    0.05
     Aad
    0.05
     front
    0.05
    orre
    0.05
     Cert
    0.05
     Bon
    0.05
    _cleanup
    0.05
    ller
    0.05
    Activations Density 0.000%

    No Known Activations