© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 257
    Prev
    Next
    INDEX
    Explanations

    terms related to computer storage media

    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
    ience
    -0.07
    nee
    -0.06
    ijk
    -0.06
    istrates
    -0.06
     Pop
    -0.06
    urette
    -0.06
    iddy
    -0.06
     flag
    -0.06
    åī
    -0.06
    cter
    -0.06
    POSITIVE LOGITS
    ILE
    0.07
    insky
    0.07
    íĴ
    0.07
    ạ
    0.07
    ãĤº
    0.06
    ÑĥнкÑĤ
    0.06
    omanip
    0.06
    STONE
    0.06
    çķĻ
    0.06
     pul
    0.06
    Activations Density 0.002%

    No Known Activations