© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5677
    Prev
    Next
    INDEX
    Explanations

    references to significant events or notable figures in popular culture or sports

    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
    олом
    -0.15
    ideographic
    -0.15
     tah
    -0.15
    ownt
    -0.14
    ollider
    -0.14
    mdi
    -0.14
    radan
    -0.14
    isine
    -0.14
    ToFront
    -0.14
    ehen
    -0.14
    POSITIVE LOGITS
     Trump
    0.26
     Zika
    0.25
     Mosul
    0.25
    Trump
    0.24
     Donald
    0.24
     Bannon
    0.23
    -Trump
    0.22
     Aleppo
    0.22
     Pokemon
    0.20
     Flynn
    0.20
    Activations Density 0.203%

    No Known Activations