© 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. 24-LLAMASCOPE-RES-32K
    11. 8917
    Prev
    Next
    INDEX
    Explanations

    references to clinical trials and the lack of diversity in participant demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     individual
    -0.15
     contrary
    -0.14
     Individual
    -0.14
     plais
    -0.13
     åĢĭ
    -0.13
    Individual
    -0.13
    æĸ°çļĦ
    -0.13
    vell
    -0.12
    à¹ij
    -0.12
     أص
    -0.12
    POSITIVE LOGITS
     sort
    0.21
     essentially
    0.19
     Essentially
    0.18
     kind
    0.16
    éĻĦè¿ij
    0.16
     sorts
    0.15
    ernet
    0.15
    sort
    0.15
    kind
    0.14
    nej
    0.14
    Activations Density 0.075%

    No Known Activations