© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 88898
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or absence of something significant or noteworthy

    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
     erotische
    -0.07
    ntax
    -0.07
    beros
    -0.07
    ntag
    -0.07
     treff
    -0.07
     geil
    -0.07
    ADIUS
    -0.07
    Pure
    -0.07
    éļĨ
    -0.07
    adera
    -0.07
    POSITIVE LOGITS
     anymore
    0.08
    /not
    0.07
    ori
    0.07
    ched
    0.06
    izable
    0.06
    ables
    0.06
     shar
    0.06
     yet
    0.05
    extr
    0.05
    epad
    0.05
    Activations Density 0.045%

    No Known Activations