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. 44262
    Prev
    Next
    INDEX
    Explanations

    terms related to color or shades of green

    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
    quan
    -0.06
    erken
    -0.06
    bounce
    -0.06
    echn
    -0.06
    ODE
    -0.06
     luk
    -0.06
     Pai
    -0.06
     ashes
    -0.06
    tics
    -0.06
    ãĥģ
    -0.05
    POSITIVE LOGITS
    igr
    0.15
    ure
    0.13
    urous
    0.13
    ant
    0.11
    ugo
    0.11
    igin
    0.10
    urette
    0.10
    ura
    0.09
    uras
    0.09
    ict
    0.09
    Activations Density 0.004%

    No Known Activations