© 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. 87867
    Prev
    Next
    INDEX
    Explanations

    references to legal terminology and court cases

    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
    esan
    -0.07
    istor
    -0.07
    abor
    -0.07
    igit
    -0.06
    IndexOf
    -0.06
    ifle
    -0.06
    odash
    -0.06
    oulouse
    -0.06
    cob
    -0.06
    ÑĢÑĮ
    -0.06
    POSITIVE LOGITS
     Seat
    0.07
    ISR
    0.07
    ker
    0.07
     Mara
    0.07
    inois
    0.06
    446
    0.06
    .Feature
    0.06
    /Common
    0.06
     Ease
    0.06
     rew
    0.06
    Activations Density 0.001%

    No Known Activations