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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 86871
    Prev
    Next
    INDEX
    Explanations

    negations and statements about financial situations

    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
    ippo
    -0.09
    resher
    -0.08
    ouve
    -0.07
    _TA
    -0.07
    ÙĪØ«
    -0.07
    icans
    -0.06
    nr
    -0.06
    ÑģеÑĢ
    -0.06
     Ingen
    -0.06
    decess
    -0.06
    POSITIVE LOGITS
     do
    0.06
     ev
    0.06
    let
    0.06
    ayne
    0.06
     man
    0.06
    KIT
    0.06
    èĭ±èªŀ
    0.06
    805
    0.05
    âĢı
    0.05
     rab
    0.05
    Activations Density 0.000%

    No Known Activations