Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4650
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to court proceedings and claims

    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
    655
    -0.06
    andle
    -0.06
    ئ
    -0.06
    lobs
    -0.06
     Fasc
    -0.06
    SingleOrDefault
    -0.06
    ean
    -0.06
    alom
    -0.06
    è¼Ķ
    -0.06
    pires
    -0.06
    POSITIVE LOGITS
     allegations
    0.13
     alleged
    0.12
     allegation
    0.11
     facts
    0.10
     claimed
    0.10
     accusations
    0.10
     charges
    0.09
     asserted
    0.09
     disputed
    0.09
     Alleg
    0.09
    Activations Density 0.034%

    No Known Activations