© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 18184
    Prev
    Next
    INDEX
    Explanations

    references to things that are left or remain unresolved

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruba
    -0.15
    .scalablytyped
    -0.15
    μβ
    -0.15
    unlikely
    -0.15
    inclusive
    -0.14
    ůr
    -0.14
     stable
    -0.14
     equ
    -0.13
     Unexpected
    -0.13
    stor
    -0.13
    POSITIVE LOGITS
     un
    0.72
     uns
    0.51
    .un
    0.51
    æľª
    0.50
     unt
    0.49
     unp
    0.49
    _un
    0.48
     unb
    0.46
    unt
    0.45
    un
    0.45
    Activations Density 0.433%

    No Known Activations