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. 9-LLAMASCOPE-RES-131K
    6. 96007
    Prev
    Next
    INDEX
    Explanations

    names or references related to people, particularly in a historical or cultural context

    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
    ouro
    -0.07
     Katz
    -0.07
     Kimber
    -0.06
     Lug
    -0.06
    ulist
    -0.06
          č↵
    -0.06
    imedia
    -0.06
    abelle
    -0.06
    eteria
    -0.06
    ông
    -0.05
    POSITIVE LOGITS
    iddi
    0.07
    ï¸
    0.07
    cth
    0.07
    rieve
    0.07
    icha
    0.06
    ÐĽÐĺ
    0.06
    _framework
    0.06
    utch
    0.06
     trừ
    0.06
    овий
    0.06
    Activations Density 0.002%

    No Known Activations