© 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. 9-LLAMASCOPE-RES-131K
    11. 95512
    Prev
    Next
    INDEX
    Explanations

    specific scientific notations or references related to physical sciences

    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
    atin
    -0.08
    åľ³
    -0.07
    echan
    -0.07
    etroit
    -0.06
    caa
    -0.06
    itters
    -0.06
    ULE
    -0.06
    æĭľ
    -0.06
    ATIC
    -0.06
    judge
    -0.06
    POSITIVE LOGITS
    ertz
    0.06
     conv
    0.06
    chin
    0.06
    #aa
    0.06
    vell
    0.06
     Trom
    0.06
    COPE
    0.06
     Conv
    0.06
     Cr
    0.06
    ìĤ¬ë¬´
    0.06
    Activations Density 0.008%

    No Known Activations