© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106814
    Prev
    Next
    INDEX
    Explanations

    references to legal terminology and concepts

    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
    ako
    -0.08
    座
    -0.07
    iteur
    -0.07
    adden
    -0.07
    ehler
    -0.07
    ewise
    -0.07
     ind
    -0.07
    OTOR
    -0.06
    arseille
    -0.06
    ertainment
    -0.06
    POSITIVE LOGITS
    ekk
    0.07
    elig
    0.07
    mann
    0.07
    .IContainer
    0.07
    ActionCreators
    0.07
    hani
    0.06
    380
    0.06
    kich
    0.06
    añ
    0.06
     elig
    0.06
    Activations Density 0.000%

    No Known Activations