© 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. 15-LLAMASCOPE-RES-131K
    11. 90104
    Prev
    Next
    INDEX
    Explanations

    job titles and roles within organizational 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
     CONST
    -0.07
    mé
    -0.06
     Levy
    -0.06
    inox
    -0.06
    MOTE
    -0.06
    ÑĢави
    -0.06
    ound
    -0.06
    arend
    -0.06
    _STANDARD
    -0.06
    ocy
    -0.06
    POSITIVE LOGITS
     Previously
    0.07
    Previously
    0.07
    igsaw
    0.06
     exerc
    0.06
    TS
    0.06
    dek
    0.06
     Curtain
    0.06
    еÐ
    0.06
    655
    0.06
     Vul
    0.06
    Activations Density 0.015%

    No Known Activations