© 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. 83067
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "the."

    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
     Ùģس
    -0.07
    иной
    -0.07
    yw
    -0.07
    æĥij
    -0.07
    RESULT
    -0.07
     Offensive
    -0.06
    ÐĽÐĺ
    -0.06
    abwe
    -0.06
    .native
    -0.06
     CONDITIONS
    -0.06
    POSITIVE LOGITS
     initial
    0.09
    wards
    0.08
    word
    0.08
    ward
    0.08
     Ùħباش
    0.08
     initially
    0.07
    words
    0.07
    effects
    0.07
     dust
    0.06
    initial
    0.06
    Activations Density 0.018%

    No Known Activations