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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 93822
    Prev
    Next
    INDEX
    Explanations

    patterns of efficacy and success in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Auxiliary verbs combined with adverbs or adjectives forming phrases that evaluate the quality, success, or status of processes, events, or conditions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    qli
    -0.07
    lotte
    -0.07
    enes
    -0.06
    OKEN
    -0.06
    appy
    -0.06
    bcm
    -0.06
    tring
    -0.06
    ģı
    -0.06
    ев
    -0.06
    rix
    -0.06
    POSITIVE LOGITS
     good
    0.08
     goede
    0.07
     excellent
    0.07
     overall
    0.07
    good
    0.07
     okay
    0.07
     æŃ
    0.06
    ائر
    0.06
    enis
    0.06
     hitch
    0.06
    Activations Density 0.063%

    No Known Activations