© 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. 29563
    Prev
    Next
    INDEX
    Explanations

    phrases that include reminders or suggestions not to forget something

    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
    antan
    -0.06
     unin
    -0.06
    kh
    -0.06
    oni
    -0.06
    is
    -0.05
    onz
    -0.05
    thon
    -0.05
    /or
    -0.05
    ab
    -0.05
    話
    -0.05
    POSITIVE LOGITS
    erdale
    0.09
    'gc
    0.08
    eten
    0.07
     to
    0.07
    $LANG
    0.07
     rằng
    0.07
    :Add
    0.07
    _DEPEND
    0.07
    USED
    0.07
    istrovstvÃŃ
    0.07
    Activations Density 0.003%

    No Known Activations