© 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. 105818
    Prev
    Next
    INDEX
    Explanations

    references to cookies and data privacy

    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
    ledi
    -0.07
    dia
    -0.06
    otes
    -0.06
    asin
    -0.06
    abras
    -0.06
    abbit
    -0.06
    nown
    -0.06
    dna
    -0.06
    Translated
    -0.06
     we
    -0.06
    POSITIVE LOGITS
    orno
    0.07
    .cookie
    0.06
    hPa
    0.06
    cret
    0.06
     NEGLIGENCE
    0.06
    оÑī
    0.06
     Ging
    0.06
    _ASSUME
    0.06
     ReturnType
    0.05
     Shaw
    0.05
    Activations Density 0.001%

    No Known Activations