© 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. 31-LLAMASCOPE-RES-32K
    11. 15552
    Prev
    Next
    INDEX
    Explanations

    references to various types of media and cultural topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onest
    -0.14
    edom
    -0.13
    onestly
    -0.12
    /basic
    -0.11
    िà¤ļ
    -0.11
    panse
    -0.11
    ืà¹ī
    -0.11
    allet
    -0.10
    ugo
    -0.10
    سÙĥ
    -0.10
    POSITIVE LOGITS
     special
    1.06
    special
    0.92
     Special
    0.88
    -special
    0.87
     SPECIAL
    0.85
    Special
    0.84
    çī¹æ®Ĭ
    0.82
     spécial
    0.79
     especial
    0.79
    _special
    0.78
    Activations Density 0.468%

    No Known Activations