© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 87890
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and self-identification

    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
    acerb
    -0.07
    kontakte
    -0.07
    typings
    -0.07
    _CPP
    -0.07
    ULE
    -0.07
    Cong
    -0.07
    iode
    -0.07
    Ĥ¬
    -0.07
    Ĥ¨
    -0.07
    SSIP
    -0.07
    POSITIVE LOGITS
     horm
    0.06
    .FileSystem
    0.06
     oblig
    0.06
     Hunters
    0.06
    hea
    0.06
    /us
    0.06
    /items
    0.05
    .Abs
    0.05
     Kent
    0.05
    åīĽ
    0.05
    Activations Density 0.022%

    No Known Activations