© 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. 94700
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistical 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
    sut
    -0.09
    ihan
    -0.07
     centralized
    -0.06
    tbl
    -0.06
    oller
    -0.06
    виÑĩ
    -0.06
     αδ
    -0.06
    tero
    -0.06
    \/\/
    -0.06
    Demon
    -0.06
    POSITIVE LOGITS
     GOODMAN
    0.07
    amient
    0.07
    amera
    0.07
    ONTAL
    0.06
    ominated
    0.06
    è§Ĥ
    0.06
    úsqueda
    0.06
     beaut
    0.06
     continua
    0.06
    Periph
    0.06
    Activations Density 0.103%

    No Known Activations