© 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. 40715
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emphasis or affirmation

    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
    رÙħ
    -0.06
    дÑĢ
    -0.06
     ÙĨÙħ
    -0.06
    aid
    -0.06
    å°ļ
    -0.06
     воÑģп
    -0.06
    гÑĢа
    -0.05
    terra
    -0.05
     Aid
    -0.05
     Craig
    -0.05
    POSITIVE LOGITS
    ovah
    0.08
    aira
    0.07
    ÑĤаж
    0.07
    egin
    0.07
    paired
    0.06
    .bunifuFlatButton
    0.06
    tee
    0.06
    antha
    0.06
    arris
    0.06
    venes
    0.06
    Activations Density 0.019%

    No Known Activations