© 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. 78311
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ever" reflecting a sense of continuous or recurring experiences

    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
    à¤Łà¤°
    -0.07
    immers
    -0.07
    xima
    -0.07
    sch
    -0.07
    parator
    -0.07
    charts
    -0.07
    scratch
    -0.06
    ernen
    -0.06
    dater
    -0.06
    ofday
    -0.06
    POSITIVE LOGITS
    theless
    0.09
    greens
    0.09
    green
    0.09
    lasting
    0.09
     since
    0.08
    last
    0.08
    thing
    0.07
    yp
    0.07
    deen
    0.07
    ly
    0.07
    Activations Density 0.008%

    No Known Activations