© 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. 78871
    Prev
    Next
    INDEX
    Explanations

    references to businesses and their professional relationships

    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
    TRS
    -0.07
    bast
    -0.07
    äºĮ人
    -0.07
    gon
    -0.07
    usercontent
    -0.07
    ãĥ³ãĥĶ
    -0.07
     Vys
    -0.07
     VERIFY
    -0.07
    ãĥīãĥ«
    -0.07
    Downloading
    -0.06
    POSITIVE LOGITS
    orman
    0.07
     multiple
    0.07
     network
    0.07
     unlike
    0.06
     underlying
    0.06
     volume
    0.06
     across
    0.06
     L
    0.06
     exclusive
    0.06
    füh
    0.06
    Activations Density 0.014%

    No Known Activations