© 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. 29035
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to protein analysis

    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
    registers
    -0.06
    ilece
    -0.06
    oth
    -0.06
    ãģ¨ãģĨ
    -0.06
    .def
    -0.06
    ستÙħ
    -0.06
    ÙĴÙĨ
    -0.06
    ehr
    -0.06
    antor
    -0.06
    askell
    -0.06
    POSITIVE LOGITS
     confidence
    0.12
     score
    0.10
     Confidence
    0.10
    confidence
    0.10
    Conf
    0.09
    99
    0.09
    -confidence
    0.09
     scores
    0.09
    -score
    0.08
    _score
    0.08
    Activations Density 0.132%

    No Known Activations