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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 77161
    Prev
    Next
    INDEX
    Explanations

    features and specifications of luxury items

    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
    ouri
    -0.08
    318
    -0.07
    igy
    -0.07
    jur
    -0.06
     arada
    -0.06
    LETE
    -0.06
    NIC
    -0.06
    chalk
    -0.06
    mime
    -0.06
    jedn
    -0.06
    POSITIVE LOGITS
    éĥİ
    0.07
     Sw
    0.07
    veal
    0.06
     vi
    0.06
     Rein
    0.06
    eref
    0.06
     Rubin
    0.06
     èĪ
    0.06
     rear
    0.06
     Diff
    0.06
    Activations Density 0.006%

    No Known Activations