© 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. 28-LLAMASCOPE-RES-32K
    11. 27024
    Prev
    Next
    INDEX
    Explanations

    mentions of products and their characteristics, particularly in relation to quality and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibus
    -0.15
    Ä©nh
    -0.15
    astos
    -0.15
    aro
    -0.15
    kees
    -0.14
    igne
    -0.14
    ibre
    -0.14
     TOR
    -0.14
    inci
    -0.14
    eldom
    -0.14
    POSITIVE LOGITS
    aku
    0.16
     ah
    0.16
    á¹
    0.16
    agit
    0.15
    ãĥĹãĥ¬
    0.15
    ah
    0.15
    NU
    0.14
    antic
    0.14
    onia
    0.14
    iah
    0.14
    Activations Density 0.048%

    No Known Activations