© 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. 106882
    Prev
    Next
    INDEX
    Explanations

    phrases related to uniqueness or distinctiveness

    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
    INF
    -0.07
    ł
    -0.06
    ancel
    -0.06
    ieux
    -0.06
    INARY
    -0.06
     çģ
    -0.06
     Barn
    -0.06
    اÙĩÙħ
    -0.06
    indi
    -0.05
    ureau
    -0.05
    POSITIVE LOGITS
     oppon
    0.07
    guns
    0.07
     Rover
    0.07
     uniquely
    0.07
    ÄĻż
    0.07
    yms
    0.07
    iad
    0.06
    ">//
    0.06
    _UNIQUE
    0.06
    unique
    0.06
    Activations Density 0.001%

    No Known Activations