© 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. 7-LLAMASCOPE-RES-32K
    11. 2000
    Prev
    Next
    INDEX
    Explanations

    key structural elements of scientific papers, such as conclusions, research methods, and keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lesia
    -0.17
    igy
    -0.16
     Hoy
    -0.15
    .Emit
    -0.14
    atsby
    -0.14
    -gnu
    -0.14
     marginal
    -0.14
     Fry
    -0.14
    modal
    -0.14
    fen
    -0.14
    POSITIVE LOGITS
    ramer
    0.15
    evi
    0.15
     Jacqu
    0.14
    Keywords
    0.14
     ãģį
    0.14
    'post
    0.14
    eyen
    0.14
    оÑĢÑĥж
    0.13
     finally
    0.13
    .scalablytyped
    0.13
    Activations Density 0.014%

    No Known Activations