Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 10691
    Prev
    Next
    INDEX
    Explanations

    preprocessor directives and class definitions in C/C++ code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    634
    -0.17
    iers
    -0.15
     Ù쨱ÙĪ
    -0.14
    acio
    -0.14
    acades
    -0.14
    eras
    -0.14
     Ker
    -0.14
     Ellison
    -0.14
    afort
    -0.14
    éric
    -0.14
    POSITIVE LOGITS
     lint
    0.17
     INCLUDED
    0.15
    orn
    0.15
     ___
    0.14
    reib
    0.14
    dk
    0.14
    stdafx
    0.14
    vr
    0.14
    ORN
    0.14
    hit
    0.14
    Activations Density 0.008%

    No Known Activations