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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 29-LLAMASCOPE-RES-32K
    6. 12726
    Prev
    Next
    INDEX
    Explanations

    references to legal regulations and Adobe software products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    جاÙħ
    -0.20
    brain
    -0.20
    Brain
    -0.19
    elib
    -0.19
     Brain
    -0.18
     brain
    -0.16
    anio
    -0.16
    eler
    -0.15
    edo
    -0.15
    .enum
    -0.15
    POSITIVE LOGITS
    uni
    0.16
     Pag
    0.15
     Ridley
    0.15
     Cecil
    0.14
    ¦
    0.14
    roach
    0.14
    ro
    0.14
    /packages
    0.14
     postage
    0.14
    ionage
    0.14
    Activations Density 0.028%

    No Known Activations