© 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. 61869
    Prev
    Next
    INDEX
    Explanations

    open parentheses and their occurrences in various contexts in the text

    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
     effect
    -0.06
    &T
    -0.06
     er
    -0.06
    lias
    -0.06
     defect
    -0.06
    ög
    -0.06
    avanaugh
    -0.05
     Fancy
    -0.05
    ],
    -0.05
    eb
    -0.05
    POSITIVE LOGITS
    HeaderValue
    0.08
    ucha
    0.07
    ocha
    0.07
    ennen
    0.07
    styl
    0.07
    erti
    0.07
    879
    0.07
    riteln
    0.07
     yyn
    0.07
    untu
    0.07
    Activations Density 0.054%

    No Known Activations