© 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. 28951
    Prev
    Next
    INDEX
    Explanations

    expressions of commendation and recognition of individuals or communities

    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
    bie
    -0.07
     Ein
    -0.07
    odesk
    -0.07
    ares
    -0.07
    afen
    -0.06
    DonaldTrump
    -0.06
    uter
    -0.06
    udu
    -0.06
    cla
    -0.06
    orsch
    -0.06
    POSITIVE LOGITS
    marsh
    0.08
     worst
    0.07
    ãĥ©ãĤ¹
    0.07
     sweep
    0.07
    ิà¹ī
    0.07
    _TM
    0.07
    _hdl
    0.07
    аÑĢаÑĤ
    0.07
    AccessType
    0.06
    bad
    0.06
    Activations Density 0.039%

    No Known Activations