© 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. 118994
    Prev
    Next
    INDEX
    Explanations

    components related to performance or mechanics in a technical context

    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
    vest
    -0.08
    ableObject
    -0.07
    åģı
    -0.06
    -widget
    -0.06
    ارس
    -0.06
    uju
    -0.06
     unten
    -0.06
    \htdocs
    -0.06
    =yes
    -0.06
    -hooks
    -0.06
    POSITIVE LOGITS
    ê
    0.06
    ahir
    0.06
    ocre
    0.06
    sak
    0.05
     Maher
    0.05
    alic
    0.05
     omas
    0.05
     Gross
    0.05
    Tube
    0.05
    ronic
    0.05
    Activations Density 0.000%

    No Known Activations