© 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. 79016
    Prev
    Next
    INDEX
    Explanations

    technical features and capabilities in audio or recording environments

    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
     Alman
    -0.07
    imoto
    -0.06
    DBus
    -0.06
     å£
    -0.06
     heaven
    -0.06
     chore
    -0.06
    ĥ
    -0.06
    ETA
    -0.06
    hower
    -0.06
    _GRANTED
    -0.06
    POSITIVE LOGITS
     studio
    0.10
     studios
    0.08
     Studio
    0.08
     Recording
    0.08
     recording
    0.08
    Phones
    0.08
    Recording
    0.08
    Studio
    0.07
    studio
    0.07
     Industry
    0.07
    Activations Density 0.022%

    No Known Activations