© 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. 77849
    Prev
    Next
    INDEX
    Explanations

    phrases that express intensity or exaggeration

    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
     ultimate
    -0.06
    bah
    -0.06
    हर
    -0.06
    sparse
    -0.06
     cÃłng
    -0.06
    ми
    -0.05
    antz
    -0.05
    elli
    -0.05
    ãĥ³ãĥĸ
    -0.05
    bir
    -0.05
    POSITIVE LOGITS
    NullOr
    0.07
     Blasio
    0.07
    UEL
    0.07
    EDIA
    0.07
    anford
    0.07
    aData
    0.07
     lot
    0.07
    atsby
    0.07
    .scala
    0.07
    usp
    0.07
    Activations Density 0.004%

    No Known Activations