© 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. 75635
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to availability or the act of becoming accessible

    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
    imas
    -0.07
    odd
    -0.07
    beh
    -0.06
    heets
    -0.06
    EMA
    -0.06
    /***/
    -0.06
    urn
    -0.06
    ulla
    -0.06
    romo
    -0.06
    सन
    -0.06
    POSITIVE LOGITS
    NAL
    0.07
    ĭ
    0.06
     Kun
    0.06
    лам
    0.06
    .bb
    0.06
     ÐłÑĥÑģ
    0.06
    AAAAAAAA
    0.06
    erokee
    0.06
     Cyril
    0.06
     PARTY
    0.06
    Activations Density 0.001%

    No Known Activations