© 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. 16813
    Prev
    Next
    INDEX
    Explanations

    references to mobile phone usage and 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
    utow
    -0.08
    oldur
    -0.07
     Lon
    -0.07
    å©Ĩ
    -0.07
    stype
    -0.06
     pregn
    -0.06
    ÙĦاØŃ
    -0.06
     bÃło
    -0.06
    .Annotations
    -0.06
    Lon
    -0.06
    POSITIVE LOGITS
    -pocket
    0.09
    895
    0.07
    phalt
    0.07
    held
    0.07
    omo
    0.06
     pocket
    0.06
     Hand
    0.06
    dzi
    0.06
    arme
    0.06
    ussy
    0.06
    Activations Density 0.029%

    No Known Activations