© 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. 30-LLAMASCOPE-RES-32K
    11. 14657
    Prev
    Next
    INDEX
    Explanations

    terms related to concepts of inclusion, decision-making, or defined actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teki
    -0.17
    aturas
    -0.16
    atal
    -0.16
     oci
    -0.15
    EIF
    -0.15
    acz
    -0.15
    acas
    -0.14
    hea
    -0.14
    ĮĴ
    -0.14
    дÑĢом
    -0.14
    POSITIVE LOGITS
    io
    0.45
     ion
    0.42
    Ion
    0.41
    ión
    0.41
     ions
    0.38
    -ion
    0.38
    ione
    0.37
    iom
    0.36
    ional
    0.35
    ió
    0.34
    Activations Density 0.046%

    No Known Activations