© 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. 94929
    Prev
    Next
    INDEX
    Explanations

    phrases indicating addition or further elaboration

    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
     Points
    -0.06
     getattr
    -0.06
    insula
    -0.06
     Morr
    -0.06
    太éĥİ
    -0.06
    anim
    -0.06
     Spar
    -0.06
    astically
    -0.06
    afen
    -0.06
    éĢ¸
    -0.06
    POSITIVE LOGITS
    keh
    0.07
    .ls
    0.07
    opher
    0.07
    òi
    0.07
    ình
    0.07
    ĵåIJį
    0.07
    ÑĢей
    0.07
    ffield
    0.06
    OSH
    0.06
    áºŃp
    0.06
    Activations Density 0.082%

    No Known Activations