© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 104134
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals with formal titles or past positions

    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
    lep
    -0.07
    oust
    -0.07
    elow
    -0.06
    ulace
    -0.06
     McCarthy
    -0.06
    ocoa
    -0.06
    sst
    -0.06
    lius
    -0.06
    breadcrumbs
    -0.06
    lew
    -0.06
    POSITIVE LOGITS
     US
    0.07
     colony
    0.06
    ruba
    0.06
    .VisualBasic
    0.06
    532
    0.06
     Colony
    0.05
    ecz
    0.05
    +","+
    0.05
     defect
    0.05
     Bere
    0.05
    Activations Density 0.036%

    No Known Activations