© 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 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. 29-LLAMASCOPE-RES-32K
    11. 1863
    Prev
    Next
    INDEX
    Explanations

    mentions of food-related products and reviews

    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
     oder
    -0.15
     Äįi
    -0.15
     Ñĩи
    -0.15
    ï¼ĮæĪĸ
    -0.14
    lest
    -0.12
    phem
    -0.11
     دÙĬ
    -0.11
    821
    -0.11
    ILLS
    -0.11
    039
    -0.10
    POSITIVE LOGITS
     and
    0.51
     vÃł
    0.42
    	and
    0.41
     и
    0.38
    and
    0.34
     ÈĻi
    0.32
     és
    0.32
     à¹ģละ
    0.31
     à¤Ķर
    0.31
     &&
    0.30
    Activations Density 5.287%

    No Known Activations