© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125390
    Prev
    Next
    INDEX
    Explanations

    information related to time and duration

    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
     lasting
    -0.09
     lasted
    -0.08
     lasts
    -0.08
     overnight
    -0.08
    lifetime
    -0.08
     Duration
    -0.07
     lifetime
    -0.07
     длиÑĤелÑĮ
    -0.07
     prolonged
    -0.07
     Jer
    -0.07
    POSITIVE LOGITS
    ckill
    0.08
    RIX
    0.08
    rien
    0.08
    ruž
    0.07
    boro
    0.07
    اÙĦÙĦÙĩ
    0.07
    úp
    0.07
    rend
    0.07
    CallCheck
    0.07
    /inet
    0.07
    Activations Density 0.156%

    No Known Activations