© 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. 15-LLAMASCOPE-RES-131K
    11. 1523
    Prev
    Next
    INDEX
    Explanations

    phrases indicating trust and assurance in service or capabilities

    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
    inen
    -0.07
     inval
    -0.07
    ÐķС
    -0.07
    èľľ
    -0.06
    yo
    -0.06
    edo
    -0.06
    esar
    -0.06
    charm
    -0.06
    ander
    -0.06
    edom
    -0.06
    POSITIVE LOGITS
    leave
    0.07
    -safe
    0.06
    arges
    0.06
    hdl
    0.06
     capable
    0.06
    orry
    0.06
    axy
    0.06
     safe
    0.06
     safer
    0.06
    ?(:
    0.06
    Activations Density 0.061%

    No Known Activations