© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103946
    Prev
    Next
    INDEX
    Explanations

    placement of the word "in" indicating location or presence

    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
     ØŃÚ©
    -0.08
    iente
    -0.08
    leck
    -0.08
    Ħĸ
    -0.08
    ebo
    -0.07
     lety
    -0.07
    coni
    -0.07
    à¸ī
    -0.07
    uckle
    -0.07
    .toolbox
    -0.07
    POSITIVE LOGITS
     solids
    0.07
     concept
    0.06
    oli
    0.05
    999
    0.05
     build
    0.05
    fol
    0.05
     tw
    0.05
     pad
    0.05
     concepts
    0.05
     show
    0.05
    Activations Density 0.000%

    No Known Activations