© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56559
    Prev
    Next
    INDEX
    Explanations

    references to documentation URLs or links

    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
    of
    -0.08
    e
    -0.08
    ood
    -0.07
    car
    -0.07
    er
    -0.07
    to
    -0.07
    eh
    -0.07
    ics
    -0.07
    can
    -0.07
    hood
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĤº
    0.08
    dum
    0.08
    ÅĤu
    0.07
    esian
    0.07
    delivr
    0.07
    dle
    0.07
    ilage
    0.07
    _marshall
    0.07
    deme
    0.07
    illary
    0.07
    Activations Density 0.002%

    No Known Activations