© 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. 57527
    Prev
    Next
    INDEX
    Explanations

    references to various levels of ability, success, or attributes in individuals or 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
     Fried
    -0.06
    oute
    -0.06
    Å¡ak
    -0.06
    á»ĩ
    -0.06
    uste
    -0.06
    ÃŃnh
    -0.06
    ỳ
    -0.06
     extras
    -0.06
    oldem
    -0.05
     Dial
    -0.05
    POSITIVE LOGITS
    æŃ£å¸¸
    0.13
     normal
    0.12
    normal
    0.11
     NORMAL
    0.09
    æĻ®éĢļ
    0.09
     conventional
    0.09
     normals
    0.08
    Normal
    0.08
     Normal
    0.08
    :normal
    0.08
    Activations Density 0.058%

    No Known Activations