© 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. 117367
    Prev
    Next
    INDEX
    Explanations

    concepts related to decision-making and situations

    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
    irsch
    -0.07
    ilde
    -0.07
     ArrayCollection
    -0.06
     sebou
    -0.06
    aths
    -0.06
    drž
    -0.06
    _FEATURE
    -0.06
    arpa
    -0.06
    ixa
    -0.06
    ayd
    -0.06
    POSITIVE LOGITS
    opsis
    0.07
    iteral
    0.07
    -focus
    0.07
    ãĥĥ
    0.06
    marshal
    0.06
    937
    0.06
    dff
    0.06
    LEM
    0.06
    enia
    0.06
    zia
    0.06
    Activations Density 0.076%

    No Known Activations