© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56647
    Prev
    Next
    INDEX
    Explanations

    phrases related to assistance or support

    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
    edback
    -0.08
    .withOpacity
    -0.07
     Enumerator
    -0.07
    illac
    -0.07
    inki
    -0.07
    -ни
    -0.07
    ighbor
    -0.07
    anyahu
    -0.07
    /respond
    -0.07
     Hilfe
    -0.07
    POSITIVE LOGITS
     us
    0.08
     me
    0.08
     to
    0.07
     you
    0.07
    fully
    0.06
    oins
    0.06
    cales
    0.06
    ens
    0.06
    X
    0.05
    w
    0.05
    Activations Density 0.020%

    No Known Activations