© 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. 82672
    Prev
    Next
    INDEX
    Explanations

    the term "consecutive" in various contexts related to time or events

    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
    Vien
    -0.08
    ÄĽÅ¾
    -0.08
    wij
    -0.08
    åī¯
    -0.08
    essler
    -0.08
    #
    -0.07
    essian
    -0.07
    isiyle
    -0.07
    jte
    -0.07
    -syntax
    -0.07
    POSITIVE LOGITS
    ively
    0.09
    mente
    0.09
    ly
    0.07
    aneously
    0.07
    entially
    0.07
    LY
    0.06
    ingly
    0.06
    vely
    0.06
    lv
    0.06
     generations
    0.06
    Activations Density 0.007%

    No Known Activations