© 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. 84294
    Prev
    Next
    INDEX
    Explanations

    references to organizations and structures related to collegiate or historic contexts

    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
    ast
    -0.07
    ount
    -0.06
     ninth
    -0.06
     tenth
    -0.05
     likeness
    -0.05
    azer
    -0.05
    amine
    -0.05
    izen
    -0.05
    ait
    -0.05
    arent
    -0.05
    POSITIVE LOGITS
    諸
    0.09
    Assignable
    0.08
    è¯
    0.08
    éĤ£äºĽ
    0.08
    Các
    0.08
    ForMember
    0.07
    acias
    0.07
    sez
    0.07
     nackte
    0.07
    bé
    0.07
    Activations Density 0.075%

    No Known Activations