© 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. 22-LLAMASCOPE-RES-131K
    11. 4243
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate numbers or quantities

    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
    uy
    -0.08
     Turnbull
    -0.08
    quet
    -0.07
    anga
    -0.07
    altet
    -0.06
    uish
    -0.06
    inh
    -0.06
    tm
    -0.06
    NON
    -0.06
    though
    -0.06
    POSITIVE LOGITS
     nor
    0.09
     not
    0.09
     count
    0.07
    yre
    0.06
     Not
    0.06
    nor
    0.06
     tern
    0.06
    há
    0.06
     nota
    0.06
    WSC
    0.06
    Activations Density 0.002%

    No Known Activations