© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80905
    Prev
    Next
    INDEX
    Explanations

    references to public relations and media management

    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
    .foundation
    -0.07
    ormsg
    -0.06
    óÅĤ
    -0.06
    pios
    -0.06
    embr
    -0.06
    /lg
    -0.06
    جار
    -0.06
    175
    -0.06
    mostly
    -0.06
     Noel
    -0.06
    POSITIVE LOGITS
     somewhere
    0.10
    غة
    0.07
     somebody
    0.07
     perhaps
    0.07
     someone
    0.07
    /releases
    0.06
     Someone
    0.06
    éłĵ
    0.06
     اÙĦتÙĨ
    0.06
    nad
    0.06
    Activations Density 0.029%

    No Known Activations