© 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. 26-LLAMASCOPE-RES-32K
    11. 4418
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    amet
    -0.16
    REW
    -0.14
    ICA
    -0.14
     côt
    -0.13
     safeg
    -0.13
    NIL
    -0.13
     _______,
    -0.13
     Jennings
    -0.13
    skill
    -0.12
     WINAPI
    -0.12
    POSITIVE LOGITS
     USA
    0.15
    uta
    0.15
    ent
    0.15
     Classical
    0.15
    ietet
    0.14
    æ¥
    0.14
    ila
    0.14
    ainter
    0.14
    ŀĭ
    0.14
    iet
    0.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.