© 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. 83195
    Prev
    Next
    INDEX
    Explanations

    explicit expressions of comparison or analogy

    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
    ansom
    -0.07
    ardi
    -0.07
    anol
    -0.07
    ĶåĽŀ
    -0.06
    bred
    -0.06
    lang
    -0.06
    ninger
    -0.06
    asil
    -0.06
    N
    -0.06
    ön
    -0.06
    POSITIVE LOGITS
    ÏģÏī
    0.08
    _cum
    0.07
    егоÑĢ
    0.07
    kaar
    0.07
    unar
    0.07
    oola
    0.06
    彦
    0.06
     Stanton
    0.06
     temper
    0.06
    jer
    0.06
    Activations Density 0.252%

    No Known Activations