© 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. 21-LLAMASCOPE-RES-32K
    11. 12222
    Prev
    Next
    INDEX
    Explanations

    incidents involving injuries and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¥ģलन
    -0.15
    Enlarge
    -0.15
    USAGE
    -0.15
    CRET
    -0.14
    herence
    -0.14
    ãĥĮ
    -0.14
    ãĥ©ãĥĥãĤ¯
    -0.14
    å¾®ç¬ij
    -0.14
    ÑģÑĮк
    -0.13
    AspNet
    -0.13
    POSITIVE LOGITS
    ách
    0.19
     multiple
    0.17
     Saturday
    0.17
     Hen
    0.16
     prelim
    0.16
     believed
    0.16
     suspect
    0.16
     Friday
    0.16
     reported
    0.15
     preliminary
    0.15
    Activations Density 0.173%

    No Known Activations