© 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. 29160
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions in 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
     Mein
    -0.07
    ãĥįãĥ«
    -0.06
    άÏĥ
    -0.06
    edo
    -0.06
    çIJĨçĶ±
    -0.06
    izik
    -0.06
     SIN
    -0.06
    _NATIVE
    -0.06
    ÅĻÃŃž
    -0.06
    voie
    -0.06
    POSITIVE LOGITS
    chai
    0.07
    omm
    0.06
    aci
    0.06
    inar
    0.06
    ahoma
    0.06
    umbnail
    0.06
    actionDate
    0.06
    TB
    0.06
    /card
    0.06
    Enumeration
    0.06
    Activations Density 0.000%

    No Known Activations