© 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. 69516
    Prev
    Next
    INDEX
    Explanations

    the verb "been" in various contexts, indicating ongoing experiences or actions

    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
    pk
    -0.07
    rai
    -0.07
    ESIS
    -0.07
    ecies
    -0.06
    fp
    -0.06
    wner
    -0.06
    pering
    -0.06
    htub
    -0.06
    asıyla
    -0.06
    _kb
    -0.06
    POSITIVE LOGITS
     since
    0.07
    ampa
    0.06
    ura
    0.06
     asked
    0.06
    ask
    0.06
     reading
    0.06
    èĤ²
    0.06
    urt
    0.06
    asi
    0.06
    _ISO
    0.06
    Activations Density 0.014%

    No Known Activations