© 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. 2836
    Prev
    Next
    INDEX
    Explanations

    negations or words indicating denial or disagreement

    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
    urry
    -0.07
     nonatomic
    -0.07
    ken
    -0.07
    OrNull
    -0.07
    yu
    -0.07
    combe
    -0.07
    åĩ¡
    -0.07
    ç¯Ħ
    -0.06
    648
    -0.06
    &M
    -0.06
    POSITIVE LOGITS
     least
    0.08
    ché
    0.07
     sure
    0.06
     unlike
    0.06
    venta
    0.06
     including
    0.06
     Least
    0.06
    ilee
    0.06
    _bitmap
    0.06
    ched
    0.06
    Activations Density 0.018%

    No Known Activations