© 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. 14-LLAMASCOPE-RES-32K
    11. 8209
    Prev
    Next
    INDEX
    Explanations

    phases or stages of medical conditions or disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÄIJT
    -0.15
    ứng
    -0.15
    ìĨĮ를
    -0.15
    htable
    -0.14
     scoop
    -0.14
    Ã¶ÄŁ
    -0.14
     toch
    -0.14
    ÃŃch
    -0.14
    à¸Ľà¸£à¸°à¸Īำ
    -0.14
    Scrollbar
    -0.13
    POSITIVE LOGITS
     stage
    0.36
     Stage
    0.27
     phase
    0.27
    éĺ¶æ®µ
    0.26
    stage
    0.26
    Stage
    0.25
    -stage
    0.23
     stages
    0.20
    _stage
    0.20
    phase
    0.19
    Activations Density 0.178%

    No Known Activations