© 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. 104220
    Prev
    Next
    INDEX
    Explanations

    time-related metrics and achievements

    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
    _MetaData
    -0.09
    rase
    -0.08
    WXYZ
    -0.08
    roti
    -0.08
    ilha
    -0.07
    ละ
    -0.07
    furt
    -0.07
    illas
    -0.07
    ÐłÑij
    -0.07
    SCII
    -0.07
    POSITIVE LOGITS
     initial
    0.06
     release
    0.06
     mere
    0.06
     its
    0.06
     merely
    0.06
     alone
    0.06
     days
    0.05
     just
    0.05
     spread
    0.05
     di
    0.05
    Activations Density 0.008%

    No Known Activations