© 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. 15-LLAMASCOPE-RES-131K
    11. 61652
    Prev
    Next
    INDEX
    Explanations

    terms related to legal consequences and sentencing

    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
     prosecuting
    -0.07
     Apt
    -0.07
    udiant
    -0.06
     Mour
    -0.06
    eyim
    -0.06
    isay
    -0.06
    ÅĻet
    -0.06
    inç
    -0.06
    eniable
    -0.06
     Eaton
    -0.06
    POSITIVE LOGITS
    448
    0.07
    undle
    0.07
    taire
    0.07
     pec
    0.06
     sentencing
    0.06
    ugar
    0.06
     dig
    0.06
     distrib
    0.06
     sentence
    0.06
     sentences
    0.06
    Activations Density 0.021%

    No Known Activations