© 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. 28917
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight positive experiences or significant achievements

    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
    ulis
    -0.08
    gener
    -0.06
    cher
    -0.06
     pl
    -0.06
    AAAA
    -0.05
    abb
    -0.05
    ined
    -0.05
     not
    -0.05
    766
    -0.05
     tandem
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.09
     Barcl
    0.07
    itespace
    0.07
    CallCheck
    0.07
    _fds
    0.07
    Ø¢Ùħد
    0.07
    adal
    0.07
     %↵↵
    0.07
    ntax
    0.07
    Intialized
    0.07
    Activations Density 0.011%

    No Known Activations