© 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. 15-LLAMASCOPE-RES-131K
    11. 87953
    Prev
    Next
    INDEX
    Explanations

    terms related to risk assessment and modeling

    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
    eyin
    -0.06
    assen
    -0.06
    ow
    -0.06
    hung
    -0.06
     Sant
    -0.06
    rr
    -0.06
     Synthetic
    -0.06
    oe
    -0.06
     proph
    -0.06
    allow
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    VILLE
    0.07
    AndView
    0.07
    spath
    0.07
    SPATH
    0.07
    :::::::::
    0.07
    λεÏħ
    0.06
    ëĿ½
    0.06
    .rdf
    0.06
    chg
    0.06
    Activations Density 0.066%

    No Known Activations