© 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. 71372
    Prev
    Next
    INDEX
    Explanations

    instances of the word "it" and variations of "is," reflecting a focus on subjectivity or assertions 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
    .sax
    -0.08
    (æĹ¥
    -0.08
    оÑĩки
    -0.08
    uco
    -0.07
    ussen
    -0.07
    :async
    -0.07
    оÑıÑĤ
    -0.07
    å®Įæķ´
    -0.07
    Dual
    -0.07
     nackte
    -0.07
    POSITIVE LOGITS
     can
    0.07
    imi
    0.06
    yt
    0.05
    core
    0.05
    thalm
    0.05
    113
    0.05
    ence
    0.05
    yat
    0.05
    anas
    0.05
     often
    0.05
    Activations Density 0.037%

    No Known Activations