© 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. 58430
    Prev
    Next
    INDEX
    Explanations

    questions and directives related to analysis and evaluation

    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
    agua
    -0.07
    zion
    -0.07
    iasi
    -0.06
    subjects
    -0.06
    Specification
    -0.06
    ÑģÑıÑĤ
    -0.06
    ellular
    -0.06
    rim
    -0.06
    Exact
    -0.06
    matter
    -0.06
    POSITIVE LOGITS
     yourself
    0.08
     briefly
    0.07
    ä¸Ģä¸ĭ
    0.07
     write
    0.06
    ene
    0.06
    ÙĤÙħ
    0.06
    Write
    0.06
     yourselves
    0.06
     answer
    0.06
     Brief
    0.06
    Activations Density 0.034%

    No Known Activations