© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97459
    Prev
    Next
    INDEX
    Explanations

    legal terminology and conditions regarding software licensing

    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
    afone
    -0.06
    beck
    -0.06
    Insensitive
    -0.06
    го
    -0.06
     recipro
    -0.05
    BaseContext
    -0.05
    idf
    -0.05
    iber
    -0.05
    orre
    -0.05
     CAM
    -0.05
    POSITIVE LOGITS
    HL
    0.07
    enschaft
    0.07
    igo
    0.07
     ëĭ¬
    0.06
    811
    0.06
    ikal
    0.06
    .Std
    0.06
    elight
    0.06
    FLT
    0.06
    ĶĦ
    0.06
    Activations Density 0.001%

    No Known Activations