© 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. 125804
    Prev
    Next
    INDEX
    Explanations

    occurrences of the auxiliary verb "was" in various contexts

    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
    arel
    -0.08
    wik
    -0.07
    ialized
    -0.07
    onen
    -0.07
    iÄĻ
    -0.06
    lung
    -0.06
     Cousins
    -0.06
    inke
    -0.06
    onte
    -0.06
    onne
    -0.06
    POSITIVE LOGITS
    agate
    0.07
    403
    0.06
     happening
    0.06
    BindingUtil
    0.06
    IPH
    0.06
    nest
    0.06
    adi
    0.06
    abe
    0.06
    glas
    0.06
    ahoma
    0.06
    Activations Density 0.008%

    No Known Activations