© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94037
    Prev
    Next
    INDEX
    Explanations

    the word "one" and its various contexts in the text

    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
    avenport
    -0.07
     quoi
    -0.07
    ationship
    -0.07
     Kemal
    -0.07
     PROGMEM
    -0.07
    .bs
    -0.07
    aktu
    -0.07
    ÙĤÛĮ
    -0.07
    decimal
    -0.07
    MOTE
    -0.07
    POSITIVE LOGITS
     can
    0.08
     oneself
    0.07
    oren
    0.07
    orang
    0.06
     Yug
    0.06
    abus
    0.06
    can
    0.06
     simply
    0.06
     ore
    0.06
    ActionCreators
    0.06
    Activations Density 0.016%

    No Known Activations