© 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. 27537
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the existence or presence of something

    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
    avn
    -0.07
    Äį
    -0.07
    idel
    -0.07
    lo
    -0.06
    NOWLED
    -0.06
    qv
    -0.06
     ie
    -0.06
    enin
    -0.06
    ddy
    -0.06
    ingen
    -0.06
    POSITIVE LOGITS
    tak
    0.07
    .maps
    0.06
    nds
    0.06
    asz
    0.06
    abled
    0.06
    Ñģем
    0.06
    .generated
    0.06
    osaur
    0.06
    icut
    0.06
    341
    0.06
    Activations Density 0.030%

    No Known Activations