© 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 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. 17-LLAMASCOPE-RES-131K
    11. 71307
    Prev
    Next
    INDEX
    Explanations

    references to "following" or related phrases indicating upcoming content or details

    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
    ARAM
    -0.07
    ิà¸ĩ
    -0.07
    anj
    -0.07
    eba
    -0.07
    象
    -0.06
    олÑĥÑĩ
    -0.06
    oris
    -0.06
    vro
    -0.06
     Superv
    -0.06
    ÑģÑĭлки
    -0.06
    POSITIVE LOGITS
    afari
    0.07
     kidd
    0.06
     WaitForSeconds
    0.06
    ierz
    0.05
    reno
    0.05
    ullen
    0.05
    olu
    0.05
     grill
    0.05
    forge
    0.05
    ÄĽÅ¾
    0.05
    Activations Density 0.002%

    No Known Activations