© 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. 54773
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizing events and advertising campaigns

    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
    Æ¡m
    -0.07
    å¤ĩ
    -0.07
    .stamp
    -0.06
     åıĪ
    -0.06
    chers
    -0.06
    tember
    -0.06
    ìĿ¼
    -0.06
    ’ÑĶ
    -0.06
    istencia
    -0.06
    endid
    -0.06
    POSITIVE LOGITS
    _RW
    0.07
    instead
    0.07
    achts
    0.07
    jte
    0.06
     FAT
    0.06
    ANGLES
    0.06
    澤
    0.06
     Mater
    0.06
    Ñĥв
    0.06
     instead
    0.06
    Activations Density 0.020%

    No Known Activations