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. 96172
    Prev
    Next
    INDEX
    Explanations

    references to online tools or resources, particularly related to searching or retrieving information

    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
    unker
    -0.06
    æ¸Ī
    -0.06
    unar
    -0.06
    ilot
    -0.06
     Sob
    -0.06
     cams
    -0.06
    _DLL
    -0.06
     аÑģ
    -0.06
     znam
    -0.05
     caps
    -0.05
    POSITIVE LOGITS
    vt
    0.07
    anya
    0.06
    NR
    0.06
    .RunWith
    0.06
    anoia
    0.06
    uki
    0.06
    roj
    0.06
    yt
    0.06
    bilir
    0.06
    istor
    0.06
    Activations Density 0.061%

    No Known Activations