© 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. 20-LLAMASCOPE-RES-32K
    11. 9142
    Prev
    Next
    INDEX
    Explanations

    references to web addresses or URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    overflow
    -0.16
    zzle
    -0.16
     sup
    -0.15
    oggles
    -0.15
    olutely
    -0.14
    ILINE
    -0.14
    orders
    -0.14
    ordinates
    -0.13
     overflow
    -0.13
    æĥħ
    -0.13
    POSITIVE LOGITS
    AO
    0.30
    (OP
    0.27
    (O
    0.25
     EO
    0.25
     AO
    0.25
    KO
    0.23
    (OS
    0.23
    EO
    0.23
     SO
    0.23
    (IO
    0.22
    Activations Density 0.275%

    No Known Activations