© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5135
    Prev
    Next
    INDEX
    Explanations

    instances of personal experiences related to service interactions and disputes

    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
    -www
    -0.06
     perhaps
    -0.06
     Cath
    -0.06
    aws
    -0.06
    pron
    -0.06
     hopefully
    -0.06
    unce
    -0.06
    ajes
    -0.05
    .Mutable
    -0.05
    zza
    -0.05
    POSITIVE LOGITS
    hind
    0.07
    imeline
    0.07
    ationToken
    0.07
     Wit
    0.06
    askell
    0.06
     bubble
    0.06
    idge
    0.06
     Numerous
    0.06
    -Origin
    0.06
    _tokenize
    0.06
    Activations Density 0.005%

    No Known Activations