© 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. 106764
    Prev
    Next
    INDEX
    Explanations

    references to risks and uncertainties in forward-looking statements

    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
    ãĥ¼ãĤº
    -0.06
    harma
    -0.06
    hea
    -0.06
    elib
    -0.06
    ä½ĵ
    -0.05
    ocos
    -0.05
     sealed
    -0.05
    sealed
    -0.05
     FieldType
    -0.05
    357
    -0.05
    POSITIVE LOGITS
     risks
    0.09
     factors
    0.08
     Ris
    0.08
     Factors
    0.08
    ÑĪиб
    0.07
    unc
    0.07
    ris
    0.07
     uncertainties
    0.07
    acin
    0.07
     assumptions
    0.07
    Activations Density 0.002%

    No Known Activations