© 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. 15-LLAMASCOPE-RES-131K
    11. 88766
    Prev
    Next
    INDEX
    Explanations

    prepositions and their contexts within sentences

    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
    unos
    -0.07
    tron
    -0.06
    orem
    -0.06
    fc
    -0.06
    ir
    -0.06
    .ValidationError
    -0.06
    upper
    -0.06
    zon
    -0.06
    utsche
    -0.06
    _
    -0.06
    POSITIVE LOGITS
    ADB
    0.08
    adt
    0.08
    ÛĮØ·
    0.07
    ÏĩÏĮ
    0.06
     tern
    0.06
    _UL
    0.06
    .Restrict
    0.06
    eks
    0.06
    arken
    0.06
    veis
    0.06
    Activations Density 0.024%

    No Known Activations