© 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. 81361
    Prev
    Next
    INDEX
    Explanations

    SQL query components related to conditions and joins

    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
    imals
    -0.07
    ucz
    -0.07
    (_,
    -0.07
    [$_
    -0.07
    Äįin
    -0.06
    @nate
    -0.06
    iyat
    -0.06
    iddet
    -0.06
    onomy
    -0.06
    ieurs
    -0.06
    POSITIVE LOGITS
     NOT
    0.06
     not
    0.06
    길
    0.06
     ABS
    0.06
    ABS
    0.06
    afx
    0.06
    /OR
    0.05
    .self
    0.05
    Auf
    0.05
    forth
    0.05
    Activations Density 0.006%

    No Known Activations