© 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. 11021
    Prev
    Next
    INDEX
    Explanations

    terms related to procedural content, specifically guidelines, claims, and legal contexts

    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
    agma
    -0.14
    cej
    -0.14
    irt
    -0.14
    407
    -0.14
    à¹Īà¸Ńม
    -0.13
    eson
    -0.13
    kul
    -0.13
    riere
    -0.13
    igin
    -0.13
    anged
    -0.12
    POSITIVE LOGITS
    (s
    1.24
    (es
    0.80
    [s
    0.70
    {s
    0.44
    (S
    0.40
    }s
    0.39
    (en
    0.37
     s
    0.36
    <s
    0.34
    (e
    0.32
    Activations Density 0.305%

    No Known Activations