© 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. 5-LLAMASCOPE-RES-131K
    11. 126997
    Prev
    Next
    INDEX
    Explanations

    job postings and employment opportunities

    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
    kowski
    -0.06
    otti
    -0.06
    çªģ
    -0.06
    arget
    -0.06
    artz
    -0.05
    emoc
    -0.05
     ed
    -0.05
    -ed
    -0.05
    äl
    -0.05
     electrical
    -0.05
    POSITIVE LOGITS
    /umd
    0.08
    IID
    0.07
    .rpm
    0.06
    _fsm
    0.06
    /items
    0.06
    gia
    0.06
    inalg
    0.06
    .Syntax
    0.06
    éłĤ
    0.06
    .getLog
    0.06
    Activations Density 0.055%

    No Known Activations