© 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. 86983
    Prev
    Next
    INDEX
    Explanations

    phrases related to offers and commitments without obligations

    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
    oa
    -0.08
    pron
    -0.07
    indir
    -0.07
     Gross
    -0.07
    ainter
    -0.06
    raci
    -0.06
    AttributeValue
    -0.06
     Manual
    -0.06
    inals
    -0.06
    _MAN
    -0.06
    POSITIVE LOGITS
     harmless
    0.12
     safe
    0.11
     Harm
    0.11
     without
    0.11
     no
    0.10
    Safe
    0.10
     nothing
    0.10
    safe
    0.10
    æĹł
    0.10
    -safe
    0.09
    Activations Density 0.068%

    No Known Activations