© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 75451
    Prev
    Next
    INDEX
    Explanations

    references to superheroes and related characters

    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
    enor
    -0.08
    UBY
    -0.07
    ts
    -0.06
    æ³ķ人
    -0.06
    insi
    -0.06
    ris
    -0.06
    æ´¥
    -0.06
    elay
    -0.06
    roi
    -0.06
    iefs
    -0.06
    POSITIVE LOGITS
     himself
    0.09
    /her
    0.08
    /she
    0.07
    iac
    0.07
     Himself
    0.07
    žel
    0.07
    -themed
    0.07
    essler
    0.07
    åĪĢ
    0.06
    éĻ£
    0.06
    Activations Density 0.011%

    No Known Activations