© 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. 126211
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to software installation and configuration

    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
    avy
    -0.08
    ÑĤÑİ
    -0.07
    osl
    -0.07
    åĩºåĵģ
    -0.07
    byn
    -0.07
    eyer
    -0.07
    raig
    -0.07
    ìĸ´ëĤĺ
    -0.07
    summ
    -0.06
     Kes
    -0.06
    POSITIVE LOGITS
     onto
    0.14
    onto
    0.13
     into
    0.10
    into
    0.08
     vÃło
    0.08
     Ont
    0.08
     Into
    0.08
    _into
    0.07
     INTO
    0.07
    Into
    0.07
    Activations Density 0.025%

    No Known Activations