© 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. 77357
    Prev
    Next
    INDEX
    Explanations

    references to time-related indicators, especially specific years and periods

    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
    BuilderInterface
    -0.07
     lite
    -0.07
    etc
    -0.07
    871
    -0.06
     etc
    -0.06
    Prompt
    -0.06
    UTERS
    -0.06
    æĮ¯ãĤĬ
    -0.06
    bonus
    -0.06
    ","+
    -0.06
    POSITIVE LOGITS
     or
    0.08
     according
    0.07
     depending
    0.07
    PIP
    0.07
    essor
    0.06
    acob
    0.06
    äll
    0.06
    oxel
    0.06
    enk
    0.06
    ukan
    0.06
    Activations Density 0.019%

    No Known Activations