© 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. 125614
    Prev
    Next
    INDEX
    Explanations

    references to "tick" or its variations in various 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
    raci
    -0.07
    aux
    -0.07
    ustin
    -0.06
    ake
    -0.06
    erie
    -0.06
    ouz
    -0.06
    ê²°
    -0.06
    ors
    -0.06
    dag
    -0.06
    ions
    -0.06
    POSITIVE LOGITS
    ety
    0.10
     Tick
    0.10
     tick
    0.09
    .Tick
    0.08
    .tick
    0.08
    tick
    0.08
     ticks
    0.08
    lish
    0.08
    abbo
    0.07
     èĩªåĬ¨çĶŁæĪIJ
    0.07
    Activations Density 0.006%

    No Known Activations