© 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. 107175
    Prev
    Next
    INDEX
    Explanations

    references to movies, particularly sequels and casting information

    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
     lc
    -0.07
    æŀľ
    -0.06
    htm
    -0.06
    .scalablytyped
    -0.06
    anko
    -0.06
    ung
    -0.06
    agic
    -0.06
     ÐŁÑĢоÑĦ
    -0.06
    utura
    -0.05
    ult
    -0.05
    POSITIVE LOGITS
    iyon
    0.07
    éĻ£
    0.07
    åde
    0.07
     stars
    0.07
    luž
    0.07
    nown
    0.07
    .recycle
    0.07
    едагог
    0.07
    åİŁ
    0.06
    _locals
    0.06
    Activations Density 0.016%

    No Known Activations