© 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. 3580
    Prev
    Next
    INDEX
    Explanations

    programming operators and conditional statements

    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
    oy
    -0.07
    oÅĽci
    -0.06
    éo
    -0.06
    ------+
    -0.06
    alchemy
    -0.06
    zcze
    -0.06
    ipo
    -0.06
    mouseenter
    -0.06
    atus
    -0.06
    Äħ
    -0.06
    POSITIVE LOGITS
    ttp
    0.07
    .gridColumn
    0.07
    ηγ
    0.07
    ãĢij,
    0.07
    å°ĸ
    0.07
    овиÑĩ
    0.07
    γκα
    0.07
    phon
    0.07
    blink
    0.06
    anel
    0.06
    Activations Density 0.026%

    No Known Activations