© 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. 18371
    Prev
    Next
    INDEX
    Explanations

    references to reading or learning activities

    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
    aver
    -0.08
    cosystem
    -0.06
    ight
    -0.06
    -loading
    -0.06
    WP
    -0.06
    acking
    -0.06
    vez
    -0.06
    ÑģÑĤиÑĤ
    -0.06
    awei
    -0.06
     каж
    -0.06
    POSITIVE LOGITS
     DISCLAIM
    0.08
    #aa
    0.07
    __$
    0.07
    noinspection
    0.06
    esiz
    0.06
    PÅĻi
    0.06
    Sense
    0.06
    elaide
    0.06
    AGER
    0.06
    pNet
    0.06
    Activations Density 0.001%

    No Known Activations