© 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. 93709
    Prev
    Next
    INDEX
    Explanations

    terms related to legal challenges or disputes

    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
    enberg
    -0.08
    ialized
    -0.07
    ÐŁÐļ
    -0.07
    olec
    -0.07
    ahl
    -0.07
    appen
    -0.06
    VIC
    -0.06
     Brennan
    -0.06
    eller
    -0.06
     TAS
    -0.06
    POSITIVE LOGITS
    /question
    0.07
     authority
    0.07
    401
    0.07
    riday
    0.07
     against
    0.07
    riz
    0.06
     validity
    0.06
     via
    0.06
    amsung
    0.06
     MethodInfo
    0.06
    Activations Density 0.010%

    No Known Activations