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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118502
    Prev
    Next
    INDEX
    Explanations

    phrases related to availability and waiting lists for services or resources

    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
    kich
    -0.08
    ìĺģ
    -0.07
    NamedQuery
    -0.07
    ë¡ľëĵľ
    -0.07
    reon
    -0.07
    laden
    -0.07
    HeaderCode
    -0.07
    .Embed
    -0.07
    .maps
    -0.07
    wire
    -0.07
    POSITIVE LOGITS
     wait
    0.13
     waiting
    0.12
     Wait
    0.10
     Waiting
    0.10
    wait
    0.09
     priority
    0.09
    Waiting
    0.09
    .wait
    0.08
    Wait
    0.08
     Priority
    0.08
    Activations Density 0.035%

    No Known Activations