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

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95335
    Prev
    Next
    INDEX
    Explanations

    professions or roles related to communication and artistry

    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
    ÑĢава
    -0.08
    Ïĥο
    -0.08
    .scalablytyped
    -0.07
    etu
    -0.07
    onces
    -0.07
    inka
    -0.07
    (çģ«
    -0.07
    @student
    -0.07
    essen
    -0.07
    culate
    -0.07
    POSITIVE LOGITS
     extra
    0.06
     teammates
    0.06
     par
    0.05
    mos
    0.05
     chick
    0.05
    ond
    0.05
     glyc
    0.05
    oir
    0.05
    os
    0.05
    rick
    0.05
    Activations Density 0.040%

    No Known Activations