© 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. 31-LLAMASCOPE-RES-32K
    11. 18008
    Prev
    Next
    INDEX
    Explanations

    references to scholarly opinion and discussions surrounding regulations and consumer behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JsonValue
    -0.12
    Ñıгом
    -0.12
    PropTypes
    -0.11
    ÙĨÚ¯ÛĮ
    -0.11
    ãģ«åĩº
    -0.11
    AZY
    -0.11
    иÑģÑĤÑĢа
    -0.11
    ãģ£ãģį
    -0.10
    ãģĤãģ®
    -0.10
    à¹īà¸Ļà¸Ĺ
    -0.10
    POSITIVE LOGITS
     however
    1.13
    however
    0.82
     HOWEVER
    0.68
     though
    0.68
     therefore
    0.68
     However
    0.68
     jedoch
    0.63
    However
    0.62
     meanwhile
    0.60
     nevertheless
    0.59
    Activations Density 1.328%

    No Known Activations