© 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. 29881
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a quantity or presence of various elements in context

    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
    vez
    -0.07
    तर
    -0.07
    uhn
    -0.07
     arada
    -0.06
    ucer
    -0.06
    _mount
    -0.06
    icans
    -0.06
    ONO
    -0.06
    crap
    -0.06
    ellig
    -0.06
    POSITIVE LOGITS
    ernes
    0.07
     of
    0.06
    .ManyToMany
    0.06
    asco
    0.06
    imli
    0.06
    ÂĢÂ
    0.06
    üven
    0.06
    CLE
    0.06
    ajs
    0.06
    nost
    0.06
    Activations Density 0.035%

    No Known Activations