© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89262
    Prev
    Next
    INDEX
    Explanations

    numerical rankings or statistics related to performance

    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
    ndx
    -0.08
    chang
    -0.08
    ÙĪÙĦÙĪج
    -0.07
    .Misc
    -0.07
    VEC
    -0.07
    ä¾ĭ
    -0.07
    hid
    -0.07
    alysis
    -0.07
    داد
    -0.07
    ulk
    -0.06
    POSITIVE LOGITS
     rout
    0.06
     imperfect
    0.06
     emb
    0.05
     battered
    0.05
    _intf
    0.05
    iors
    0.05
     decre
    0.05
    aire
    0.05
    iram
    0.05
    10
    0.05
    Activations Density 0.001%

    No Known Activations