© 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. 15-LLAMASCOPE-RES-131K
    11. 26488
    Prev
    Next
    INDEX
    Explanations

    terms related to permissions and allowances

    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
    zelf
    -0.07
    openh
    -0.07
    oppable
    -0.07
    sik
    -0.07
    illow
    -0.07
    zung
    -0.07
    ouflage
    -0.07
    SqlConnection
    -0.06
    posium
    -0.06
    presso
    -0.06
    POSITIVE LOGITS
    ance
    0.09
    ings
    0.08
    able
    0.08
    ances
    0.08
    ingly
    0.07
    ages
    0.07
    rence
    0.07
    esc
    0.07
    amac
    0.07
    ед
    0.07
    Activations Density 0.017%

    No Known Activations