© 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. 17-LLAMASCOPE-RES-131K
    11. 130021
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and terms indicating personal connections or significance

    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
    Browsable
    -0.06
    reh
    -0.06
    ÅĦ
    -0.06
    unal
    -0.06
    åĬ¨
    -0.06
    eh
    -0.05
     OnInit
    -0.05
     Sci
    -0.05
     Shell
    -0.05
    lah
    -0.05
    POSITIVE LOGITS
    errat
    0.07
    kke
    0.07
    peon
    0.07
    oleÄį
    0.07
    rive
    0.07
    ingleton
    0.06
    turnstile
    0.06
    Via
    0.06
    gre
    0.06
    кÑĢеÑĤ
    0.06
    Activations Density 0.000%

    No Known Activations