© 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. 77726
    Prev
    Next
    INDEX
    Explanations

    intensifiers that emphasize the degree of adjectives or adverbs

    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
     èī¯
    -0.06
    .gdx
    -0.06
     Fraction
    -0.06
    nable
    -0.06
    kos
    -0.06
    INET
    -0.06
     Ñĩи
    -0.06
    TM
    -0.06
    _CY
    -0.06
    863
    -0.06
    POSITIVE LOGITS
    unde
    0.08
    ayi
    0.07
    oty
    0.07
     rampant
    0.06
    yne
    0.06
    ÃŃst
    0.06
    ais
    0.06
    ourd
    0.06
    lag
    0.06
    aylor
    0.06
    Activations Density 0.030%

    No Known Activations