© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84089
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "is" and variations of its form

    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
    lein
    -0.09
    arian
    -0.08
    ÅĻi
    -0.07
    edis
    -0.07
    extra
    -0.07
    uls
    -0.06
    kle
    -0.06
    urs
    -0.06
    ÑĻ
    -0.06
     Lawson
    -0.06
    POSITIVE LOGITS
    echan
    0.07
    ERO
    0.06
    oreach
    0.06
    otel
    0.06
    iams
    0.06
    omers
    0.06
     mát
    0.06
    /w
    0.06
    веÑī
    0.06
    abelle
    0.06
    Activations Density 0.002%

    No Known Activations