© 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. 126991
    Prev
    Next
    INDEX
    Explanations

    phrases that express opinions or commentary on various subjects

    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
    antee
    -0.08
    ield
    -0.07
    ucha
    -0.07
    à¸Ļà¸Ķ
    -0.07
    átka
    -0.07
    ally
    -0.07
    òi
    -0.06
     Eb
    -0.06
    çĦ¶èĢĮ
    -0.06
    aid
    -0.06
    POSITIVE LOGITS
     majority
    0.08
     Majority
    0.08
    iros
    0.07
    hek
    0.07
    kü
    0.07
    _strerror
    0.06
    NAL
    0.06
     Truy
    0.06
    ÑĢап
    0.06
    tae
    0.06
    Activations Density 0.048%

    No Known Activations