© 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. 56441
    Prev
    Next
    INDEX
    Explanations

    references to employment and related roles within various organizations, particularly in government and corporate contexts

    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
    uco
    -0.07
    rij
    -0.07
    arden
    -0.07
    iloc
    -0.06
     obt
    -0.06
    dana
    -0.06
    UIBarButtonItem
    -0.06
    ubar
    -0.06
    OME
    -0.06
     Juliet
    -0.06
    POSITIVE LOGITS
    allon
    0.07
    oes
    0.07
    grave
    0.06
    .getSystemService
    0.06
     Ñģклада
    0.06
     turno
    0.06
    åĩºçīĪ社
    0.06
    pras
    0.06
     company
    0.06
     companies
    0.06
    Activations Density 0.024%

    No Known Activations