© 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. 128508
    Prev
    Next
    INDEX
    Explanations

    terms related to exemptions and waivers in legal or regulatory contexts

    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
    ISIBLE
    -0.08
    elligence
    -0.08
    rani
    -0.08
    ------+------+
    -0.07
    aida
    -0.07
    /video
    -0.07
    /people
    -0.07
    лиÑĩ
    -0.07
    leh
    -0.07
    _PWM
    -0.07
    POSITIVE LOGITS
     for
    0.08
     granted
    0.07
    808
    0.07
     Ink
    0.07
     rel
    0.07
     em
    0.06
    erez
    0.06
     длÑı
    0.06
     ink
    0.06
    ez
    0.06
    Activations Density 0.006%

    No Known Activations