© 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. 118654
    Prev
    Next
    INDEX
    Explanations

    references to glamor and its variations in context

    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
    naments
    -0.08
    eve
    -0.07
    edly
    -0.07
    oldem
    -0.07
    gies
    -0.07
    ÑģилÑĮ
    -0.07
    anka
    -0.07
    .maps
    -0.07
    омÑĸ
    -0.07
    Strength
    -0.07
    POSITIVE LOGITS
    ming
    0.07
    tier
    0.07
    ier
    0.07
     quotient
    0.07
    orous
    0.06
    ouflage
    0.06
    ti
    0.06
    iness
    0.06
    tic
    0.06
    ification
    0.06
    Activations Density 0.002%

    No Known Activations