© 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 EvalsExportsAPI 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. 93789
    Prev
    Next
    INDEX
    Explanations

    phrases related to guidance or advice involving thresholds and boundaries

    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
    enci
    -0.08
    icut
    -0.07
     sol
    -0.06
     cas
    -0.06
    (IDC
    -0.06
    inston
    -0.06
    ,param
    -0.06
    pii
    -0.06
     district
    -0.06
     forte
    -0.06
    POSITIVE LOGITS
    .untracked
    0.08
    zag
    0.06
    chwitz
    0.06
    uppe
    0.06
    Scaler
    0.06
     Software
    0.06
    åĩĿ
    0.06
    oeff
    0.06
    Software
    0.06
     forks
    0.06
    Activations Density 0.000%

    No Known Activations