© 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. 71343
    Prev
    Next
    INDEX
    Explanations

    key concepts related to business strategy and management

    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
    onet
    -0.07
     folks
    -0.07
     POLITICO
    -0.07
     Waterloo
    -0.07
    mlin
    -0.06
    ocab
    -0.06
    -plus
    -0.06
    áš
    -0.06
    acier
    -0.06
    akash
    -0.06
    POSITIVE LOGITS
    åŃĺäºİ
    0.07
    ustralian
    0.07
    еком
    0.07
    [^
    0.06
    èĥ½å¤Ł
    0.06
    á»ģ
    0.06
     Abram
    0.06
    tir
    0.06
    -Jun
    0.06
    quisite
    0.06
    Activations Density 0.002%

    No Known Activations