Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95921
    Prev
    Next
    INDEX
    Explanations

    words indicating capability or suitability, particularly those ending in 'able'

    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
    ing
    -0.08
    ed
    -0.08
    ese
    -0.08
    ãĤ¥
    -0.07
    egal
    -0.07
    asso
    -0.07
    edb
    -0.07
    arily
    -0.07
    kowski
    -0.07
    el
    -0.07
    POSITIVE LOGITS
    heid
    0.09
    -bodied
    0.09
     Jar
    0.07
    uchar
    0.07
    ilty
    0.07
    yg
    0.07
    머ëĭĪ
    0.07
    ãĥ¼ãĥĹ
    0.07
    ipsis
    0.06
    Jar
    0.06
    Activations Density 0.072%

    No Known Activations