© 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. 17-LLAMASCOPE-RES-131K
    6. 84185
    Prev
    Next
    INDEX
    Explanations

    phrases indicating subjective appreciation or evaluation of songs and related 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
    okes
    -0.06
    uch
    -0.06
    atin
    -0.06
    .tf
    -0.06
     tieten
    -0.06
    engers
    -0.06
    gee
    -0.06
    lettes
    -0.06
    esso
    -0.06
     Negro
    -0.06
    POSITIVE LOGITS
    onta
    0.07
    inea
    0.07
    ÃĹ↵↵
    0.07
    бав
    0.07
    oulder
    0.07
     yoksa
    0.07
     Ulus
    0.06
    ancia
    0.06
    "type
    0.06
    elop
    0.06
    Activations Density 0.016%

    No Known Activations