© 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. 87342
    Prev
    Next
    INDEX
    Explanations

    guidelines related to safety and care for children during events like Halloween

    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
    zos
    -0.07
    otas
    -0.06
     borders
    -0.06
     Maurit
    -0.06
    uggage
    -0.06
    OTA
    -0.06
    egl
    -0.05
    zsche
    -0.05
     Perl
    -0.05
    urret
    -0.05
    POSITIVE LOGITS
    addtogroup
    0.06
    PEC
    0.06
    vice
    0.06
    bers
    0.06
     bully
    0.06
    esan
    0.06
    foy
    0.06
    íģ¬
    0.06
    taire
    0.06
    pons
    0.06
    Activations Density 0.002%

    No Known Activations