© 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. 5-LLAMASCOPE-RES-131K
    11. 126650
    Prev
    Next
    INDEX
    Explanations

    references to high points or peaks, particularly in geographical or abstract 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
    reon
    -0.07
    eck
    -0.07
    eme
    -0.07
     Bond
    -0.06
    emark
    -0.06
    inging
    -0.06
    rc
    -0.06
    eam
    -0.06
     Booth
    -0.06
    rgan
    -0.06
    POSITIVE LOGITS
    maal
    0.07
    lep
    0.07
    abant
    0.07
    íĭ
    0.07
    aye
    0.07
    sten
    0.07
    éħ
    0.07
    keit
    0.06
    lsru
    0.06
    åħĭæĸ¯
    0.06
    Activations Density 0.000%

    No Known Activations