© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17739
    Prev
    Next
    INDEX
    Explanations

    topics related to scientific research and methodologies

    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
    одаÑĢ
    -0.15
    ãĥĨãĥ«
    -0.14
    mes
    -0.14
     Crate
    -0.13
    uge
    -0.13
     discre
    -0.13
    alse
    -0.13
    @Web
    -0.13
     serialVersionUID
    -0.13
     blat
    -0.12
    POSITIVE LOGITS
    aho
    0.19
    hest
    0.16
    haft
    0.14
    edii
    0.14
    acas
    0.14
    è°±
    0.14
     [#
    0.13
    ethod
    0.13
    виÑĩ
    0.13
    eldorf
    0.13
    Activations Density 0.022%

    No Known Activations