© 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. 56073
    Prev
    Next
    INDEX
    Explanations

    conditional statements or phrases indicating dependencies or requirements

    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
    angstrom
    -0.07
    itudes
    -0.06
    ago
    -0.06
    setPosition
    -0.06
    aise
    -0.06
     RC
    -0.06
    ici
    -0.06
     maduras
    -0.06
    urst
    -0.06
    oding
    -0.06
    POSITIVE LOGITS
    arel
    0.07
     requested
    0.07
     need
    0.07
     needs
    0.07
    anks
    0.07
    aben
    0.06
    ë³ij
    0.06
    onavir
    0.06
     Fior
    0.06
    bservice
    0.06
    Activations Density 0.010%

    No Known Activations