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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-32K
    11. 19943
    Prev
    Next
    INDEX
    Explanations

    references to hockey coaches and their comments or actions related to team dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     opak
    -0.17
    chten
    -0.17
    opak
    -0.15
    lane
    -0.14
    ردد
    -0.14
    迪
    -0.14
    ventus
    -0.14
    onne
    -0.14
    idla
    -0.14
    ÏİÏĤ
    -0.13
    POSITIVE LOGITS
     wise
    0.15
    arkin
    0.14
    otic
    0.14
     YY
    0.14
    ar
    0.14
     gang
    0.14
     Kund
    0.14
     comb
    0.14
     government
    0.14
    iken
    0.13
    Activations Density 0.056%

    No Known Activations