© 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 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. 60901
    Prev
    Next
    INDEX
    Explanations

    references to educational or instructional materials

    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
    ifter
    -0.08
    unga
    -0.07
    ربÙĩ
    -0.07
    ormsg
    -0.06
    ëį°
    -0.06
    uzz
    -0.06
     competence
    -0.06
    addtogroup
    -0.06
    år
    -0.06
    ÑĢоÑģÑĤ
    -0.06
    POSITIVE LOGITS
    shop
    0.08
    ends
    0.08
    -style
    0.07
    ç±į
    0.07
    -like
    0.07
    sWith
    0.07
    iat
    0.07
    -esque
    0.07
    etch
    0.07
    les
    0.06
    Activations Density 0.011%

    No Known Activations