© 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. 105810
    Prev
    Next
    INDEX
    Explanations

    references to radio shows and music-related content

    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
     Forums
    -0.07
    arse
    -0.07
    _QMARK
    -0.06
    ìĭľìĺ¤
    -0.06
     Photos
    -0.06
    icho
    -0.06
     seasons
    -0.06
    oreach
    -0.06
    ervices
    -0.06
    alone
    -0.06
    POSITIVE LOGITS
     selections
    0.07
    .datas
    0.07
     seg
    0.07
     selection
    0.07
     featured
    0.06
     tonight
    0.06
     exempl
    0.06
     callers
    0.06
     olsun
    0.06
     featuring
    0.06
    Activations Density 0.007%

    No Known Activations