© 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. 3659
    Prev
    Next
    INDEX
    Explanations

    phrases related to iconic characters and franchises

    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
     denomin
    -0.07
    ibbon
    -0.06
     Hogwarts
    -0.06
    inator
    -0.06
    /***/
    -0.06
    ">//
    -0.06
     taille
    -0.06
    ivet
    -0.06
    eless
    -0.06
    кол
    -0.06
    POSITIVE LOGITS
     popular
    0.08
     franchise
    0.08
     Popular
    0.07
     series
    0.07
     originally
    0.07
    çĶ²
    0.07
    agar
    0.07
     série
    0.06
    popular
    0.06
     decades
    0.06
    Activations Density 0.016%

    No Known Activations