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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 4284
    Prev
    Next
    INDEX
    Explanations

    references to paragraphs or content structure within texts

    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
    adoo
    -0.08
    kit
    -0.08
    -alert
    -0.07
    feito
    -0.07
    ipay
    -0.07
    .Loader
    -0.07
    uft
    -0.07
    usb
    -0.07
    way
    -0.07
    WAY
    -0.07
    POSITIVE LOGITS
    -long
    0.10
    al
    0.10
    arians
    0.10
    ed
    0.09
    arian
    0.09
    naire
    0.09
    aire
    0.09
    ÙĨ
    0.08
    ical
    0.08
    naires
    0.07
    Activations Density 0.004%

    No Known Activations