© 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. 70390
    Prev
    Next
    INDEX
    Explanations

    references to media organizations and their roles in reporting

    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
    лÑİд
    -0.07
    湿
    -0.06
    æĻ¯
    -0.06
    μι
    -0.06
     اعÙħاÙĦ
    -0.06
    ä¿ĿéĻ©
    -0.06
    ">#
    -0.06
    Uploaded
    -0.05
    æĸŃ
    -0.05
    aris
    -0.05
    POSITIVE LOGITS
    ameda
    0.08
    imed
    0.08
     Sender
    0.07
     Voice
    0.07
     ç·
    0.07
    owi
    0.07
     Leaf
    0.07
    yen
    0.07
     operation
    0.06
     Gros
    0.06
    Activations Density 0.003%

    No Known Activations