© 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. 124256
    Prev
    Next
    INDEX
    Explanations

    references to the character Cliff or the concept of a "cliffhanger" in narrative contexts

    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
    ope
    -0.07
     Licht
    -0.07
    uka
    -0.06
    нед
    -0.06
    CP
    -0.06
    terra
    -0.06
     bufsize
    -0.06
    fds
    -0.06
    ozy
    -0.06
    oved
    -0.06
    POSITIVE LOGITS
    side
    0.09
    inary
    0.08
     bare
    0.07
    ullo
    0.07
    enko
    0.07
    ORD
    0.07
    sonian
    0.07
    swer
    0.07
    stein
    0.07
    iten
    0.07
    Activations Density 0.004%

    No Known Activations