© 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. 88078
    Prev
    Next
    INDEX
    Explanations

    references to legal and governmental processes or actions

    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
    дам
    -0.07
    enstein
    -0.07
    080
    -0.07
    icz
    -0.07
    ettel
    -0.07
    æŁ³
    -0.06
    912
    -0.06
    .volley
    -0.06
    TypeEnum
    -0.06
    299
    -0.06
    POSITIVE LOGITS
     grant
    0.07
     Grant
    0.07
     granting
    0.07
     award
    0.07
    iful
    0.07
     grants
    0.06
    grant
    0.06
    ext
    0.06
     allow
    0.06
    gra
    0.06
    Activations Density 0.037%

    No Known Activations