© 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. 41039
    Prev
    Next
    INDEX
    Explanations

    locations or settings described in various contexts

    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
    apult
    -0.08
    ventus
    -0.07
    quier
    -0.07
    etch
    -0.07
    odyn
    -0.07
    rift
    -0.07
    itsu
    -0.07
    dsl
    -0.07
    veal
    -0.07
     Vern
    -0.07
    POSITIVE LOGITS
     until
    0.08
    until
    0.08
    ymi
    0.07
     Until
    0.06
    IOC
    0.06
    arning
    0.06
    _until
    0.06
    سر
    0.06
    without
    0.06
    eren
    0.06
    Activations Density 0.053%

    No Known Activations