© 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. 5-LLAMASCOPE-RES-131K
    11. 126708
    Prev
    Next
    INDEX
    Explanations

    comparisons and expressions of uniqueness

    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
    izin
    -0.07
    ouv
    -0.07
     Osman
    -0.07
     stranger
    -0.07
    sez
    -0.07
    osc
    -0.06
    beck
    -0.06
    ÙĤÛĮ
    -0.06
    ácil
    -0.06
    (æ°´
    -0.06
    POSITIVE LOGITS
    ockey
    0.07
    ehr
    0.06
    OfClass
    0.06
    ToInt
    0.06
    idend
    0.06
    itere
    0.06
    íķĺëĬĶëį°
    0.06
    indent
    0.06
    alto
    0.06
     Covent
    0.06
    Activations Density 0.002%

    No Known Activations