© 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. 6-LLAMASCOPE-RES-32K
    11. 8376
    Prev
    Next
    INDEX
    Explanations

    segments indicating video or media content, particularly teasers and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andon
    -0.16
    elves
    -0.16
    outh
    -0.15
    ozem
    -0.15
    ibold
    -0.14
    PT
    -0.14
     disappe
    -0.14
     bapt
    -0.14
    agt
    -0.13
    >manual
    -0.13
    POSITIVE LOGITS
    lemn
    0.17
    ë¹Ī
    0.14
     vac
    0.14
    tree
    0.14
    anging
    0.13
     icing
    0.13
    _salt
    0.13
    æ¤ħ
    0.13
    lique
    0.13
     tempor
    0.13
    Activations Density 0.004%

    No Known Activations