© 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 EvalsExportsAPI 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. 128953
    Prev
    Next
    INDEX
    Explanations

    themes of communication barriers and personal identity struggles

    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
    eree
    -0.07
    abei
    -0.07
    urch
    -0.07
    strand
    -0.07
    usto
    -0.06
    áºł
    -0.06
    otten
    -0.06
    htdocs
    -0.06
    ates
    -0.06
    ife
    -0.06
    POSITIVE LOGITS
     deform
    0.07
    asser
    0.07
     break
    0.06
     lag
    0.06
     perceived
    0.06
     unconventional
    0.06
     acne
    0.06
     ung
    0.06
    agini
    0.06
     poverty
    0.06
    Activations Density 0.021%

    No Known Activations