Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 43728
    Prev
    Next
    INDEX
    Explanations

    themes related to dreams and aspirations

    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
    unik
    -0.07
    undra
    -0.07
    ampler
    -0.06
    aign
    -0.06
    pread
    -0.06
    ewise
    -0.06
    etration
    -0.06
    gratis
    -0.06
    umd
    -0.06
     gratuits
    -0.06
    POSITIVE LOGITS
    catch
    0.14
    like
    0.13
    land
    0.13
    ers
    0.13
    boat
    0.13
    y
    0.12
    er
    0.12
    time
    0.12
    iest
    0.12
     deferred
    0.11
    Activations Density 0.020%

    No Known Activations