© 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. 5-LLAMASCOPE-RES-131K
    11. 125652
    Prev
    Next
    INDEX
    Explanations

    possessive forms and contractions

    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
     Duy
    -0.06
    iff
    -0.06
    aly
    -0.06
     branch
    -0.06
    ãĤīãģĹãģĦ
    -0.06
    hs
    -0.06
    DAQ
    -0.06
    boa
    -0.06
     Geschichte
    -0.06
    325
    -0.06
    POSITIVE LOGITS
    asaki
    0.08
     why
    0.07
    seau
    0.07
    obi
    0.06
     slee
    0.06
    ãĥªãĥ¼ãĤº
    0.06
    /groups
    0.06
     Hentai
    0.06
    gesi
    0.06
    inson
    0.06
    Activations Density 0.026%

    No Known Activations