© 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. 12-LLAMASCOPE-RES-32K
    11. 31631
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific products and their categories, particularly in the context of motorcycles, Christmas items, and dogs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mang
    -0.14
     Vict
    -0.14
     Tob
    -0.13
     Nude
    -0.13
    оÑıÑĤ
    -0.13
     باÙĦÙħ
    -0.13
     scal
    -0.13
     tok
    -0.13
    eff
    -0.13
    onz
    -0.13
    POSITIVE LOGITS
    Å¡ka
    0.17
    allis
    0.15
    ummer
    0.15
    ardo
    0.14
    npos
    0.14
    Ľi
    0.14
    SED
    0.14
     ACCEPT
    0.14
    _pressure
    0.13
     obdob
    0.13
    Activations Density 0.065%

    No Known Activations