© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84740
    Prev
    Next
    INDEX
    Explanations

    phrases indicating thoroughness, attention to detail, and positive feedback in evaluations or reviews

    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
    utin
    -0.08
    mw
    -0.07
    ich
    -0.06
    оÑģÑĤаÑĤ
    -0.06
    /vector
    -0.06
     neutrality
    -0.06
     Král
    -0.06
     Heath
    -0.06
    ICH
    -0.06
    ä¿
    -0.06
    POSITIVE LOGITS
     missed
    0.25
    miss
    0.20
     Miss
    0.19
     miss
    0.18
     misses
    0.18
     overlooked
    0.17
    Miss
    0.17
     overlook
    0.15
     MISS
    0.15
    _miss
    0.15
    Activations Density 0.093%

    No Known Activations