© 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. 61440
    Prev
    Next
    INDEX
    Explanations

    important terms and numerical data that indicate significance or distinction

    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
    471
    -0.07
     Franken
    -0.07
    uai
    -0.06
    Å¡ÃŃm
    -0.06
    orts
    -0.06
    ople
    -0.06
    _pulse
    -0.06
    оÑīи
    -0.06
    ieces
    -0.06
    ertz
    -0.06
    POSITIVE LOGITS
    /sign
    0.07
    LOAT
    0.07
    ussen
    0.07
    COPE
    0.07
    alm
    0.07
    uent
    0.06
    OLID
    0.06
    r
    0.06
    alar
    0.06
    cased
    0.06
    Activations Density 0.010%

    No Known Activations