© 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. 15-LLAMASCOPE-RES-131K
    11. 87174
    Prev
    Next
    INDEX
    Explanations

    words related to resources, structure, and organization in technical contexts

    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
    eld
    -0.10
    ey
    -0.09
    ะ
    -0.09
    ex
    -0.09
    em
    -0.09
    ene
    -0.09
    enh
    -0.08
    et
    -0.08
    els
    -0.08
    ens
    -0.08
    POSITIVE LOGITS
    hyth
    0.10
    er
    0.10
    ighth
    0.09
    hythm
    0.09
    iginal
    0.09
    idge
    0.08
    uncated
    0.08
    ong
    0.08
    illo
    0.07
    erer
    0.07
    Activations Density 0.201%

    No Known Activations