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. 22-LLAMASCOPE-RES-131K
    6. 5510
    Prev
    Next
    INDEX
    Explanations

    terms related to electronics and computing

    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
    लब
    -0.07
    Ħĸ
    -0.07
    aira
    -0.07
    akah
    -0.07
    errat
    -0.07
    éné
    -0.07
    ocos
    -0.07
    ume
    -0.07
     Jug
    -0.06
    .experimental
    -0.06
    POSITIVE LOGITS
     obviously
    0.06
    ìĿ´ëĤĺ
    0.06
    bgcolor
    0.06
    adlo
    0.06
    Æ¡
    0.06
    _BOTH
    0.05
     tuz
    0.05
    kor
    0.05
    pose
    0.05
    ahl
    0.05
    Activations Density 0.072%

    No Known Activations