© 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. 22-LLAMASCOPE-RES-131K
    11. 3708
    Prev
    Next
    INDEX
    Explanations

    adjectives that convey a high degree of quality or positive sentiment

    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
    aña
    -0.08
    clusions
    -0.07
    leans
    -0.07
    _parms
    -0.07
    tout
    -0.07
    bies
    -0.07
    mares
    -0.07
    ertz
    -0.07
    _compat
    -0.06
    inerary
    -0.06
    POSITIVE LOGITS
     example
    0.09
     aspect
    0.08
     part
    0.07
     recent
    0.07
     siden
    0.07
     Example
    0.07
    URT
    0.06
    éĥ¨åĪĨ
    0.06
     question
    0.06
     majority
    0.06
    Activations Density 0.080%

    No Known Activations