© 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. 17-LLAMASCOPE-RES-131K
    11. 71987
    Prev
    Next
    INDEX
    Explanations

    references to music albums and collections

    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
     trom
    -0.06
    ansson
    -0.06
    antis
    -0.06
    Å¡ak
    -0.06
     networks
    -0.06
    erin
    -0.06
    avig
    -0.06
     Shipping
    -0.05
    ãĥ³ãĥķ
    -0.05
    _retry
    -0.05
    POSITIVE LOGITS
     Greatest
    0.08
    arrant
    0.07
    缤
    0.07
    ivec
    0.07
    selection
    0.07
     greatest
    0.07
    .scal
    0.07
    åĩĿ
    0.07
    รวม
    0.07
    erti
    0.06
    Activations Density 0.038%

    No Known Activations