© 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. 17-LLAMASCOPE-RES-131K
    11. 54094
    Prev
    Next
    INDEX
    Explanations

    unique and distinctive features 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
    onse
    -0.07
    èµ·
    -0.06
    izz
    -0.06
    æŀ
    -0.06
     Interface
    -0.06
    ieties
    -0.06
    ãĥĬãĥ«
    -0.06
    ando
    -0.06
    _nullable
    -0.06
    lisi
    -0.06
    POSITIVE LOGITS
     unique
    0.15
     uniqueness
    0.14
    unique
    0.14
     Unique
    0.13
    Unique
    0.13
     UNIQUE
    0.12
    (unique
    0.10
     uniq
    0.10
     uniquely
    0.10
     único
    0.10
    Activations Density 0.049%

    No Known Activations