© 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. 2-LLAMASCOPE-RES-32K
    11. 7451
    Prev
    Next
    INDEX
    Explanations

    terms related to synthesis and synthesizing processes 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 @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inned
    -0.16
    nd
    -0.15
     lif
    -0.15
    iform
    -0.15
    ined
    -0.15
    ÃŃd
    -0.15
     Lange
    -0.14
    INET
    -0.14
     Lif
    -0.14
     motor
    -0.14
    POSITIVE LOGITS
    kova
    0.16
     fisse
    0.15
    stract
    0.15
    uble
    0.15
     synthetic
    0.14
    opoulos
    0.14
    ingleton
    0.14
    Ľå»º
    0.14
    PLUGIN
    0.14
    VRT
    0.14
    Activations Density 0.014%

    No Known Activations