© 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. 4354
    Prev
    Next
    INDEX
    Explanations

    references to audio or music-related content in transcripts

    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
    asher
    -0.07
    å«
    -0.06
    icro
    -0.06
    ÏĦοκ
    -0.05
     Computing
    -0.05
     Bols
    -0.05
    elsen
    -0.05
    irim
    -0.05
     yet
    -0.05
    indow
    -0.05
    POSITIVE LOGITS
    ãĥ¼ãĥĭ
    0.08
    .SizeType
    0.07
    NameValuePair
    0.07
    .SizeF
    0.07
    URLException
    0.07
    figcaption
    0.07
    _gallery
    0.07
    STACK
    0.07
     Norris
    0.07
     resourceId
    0.07
    Activations Density 0.003%

    No Known Activations