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

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 96306
    Prev
    Next
    INDEX
    Explanations

    terms related to educational programs and partnerships

    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
    lamaya
    -0.07
    inator
    -0.06
    .vaadin
    -0.06
     Pun
    -0.06
    licht
    -0.06
    _PF
    -0.06
    nett
    -0.06
    áct
    -0.06
    aths
    -0.06
    Ｖ
    -0.06
    POSITIVE LOGITS
     Cornell
    0.06
    å¾
    0.06
     Hunting
    0.06
    OTES
    0.06
     Devon
    0.06
     assembling
    0.05
    otted
    0.05
    emi
    0.05
    odo
    0.05
    arming
    0.05
    Activations Density 0.026%

    No Known Activations