© 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. 106955
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and their implications

    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
    ube
    -0.07
    รà¸ģ
    -0.07
    YD
    -0.07
    afil
    -0.07
    è¨Ģãģ£ãģ¦
    -0.07
    affe
    -0.06
    obic
    -0.06
    QRST
    -0.06
    enti
    -0.06
    ostel
    -0.06
    POSITIVE LOGITS
     compatibility
    0.10
     mutual
    0.10
     Mutual
    0.08
     compatible
    0.08
     Compatibility
    0.07
     compat
    0.07
    compat
    0.07
     matches
    0.07
    -compatible
    0.07
     Compatible
    0.07
    Activations Density 0.000%

    No Known Activations