© 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. 30241
    Prev
    Next
    INDEX
    Explanations

    negations or contractions that express denial or absence

    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
     no
    -0.07
    yük
    -0.06
    nox
    -0.06
     not
    -0.06
     mostly
    -0.06
    085
    -0.06
    ارج
    -0.06
     Emer
    -0.06
     both
    -0.06
     Formation
    -0.06
    POSITIVE LOGITS
     necessarily
    0.13
     anymore
    0.10
    ori
    0.09
    ched
    0.09
    CHED
    0.08
    ecessarily
    0.08
    ches
    0.08
    ional
    0.07
     rocket
    0.07
    ables
    0.07
    Activations Density 0.071%

    No Known Activations