Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 10751
    Prev
    Next
    INDEX
    Explanations

    key attributes and accomplishments of notable actors and actresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aller
    -0.16
    /entity
    -0.15
    ãĥ³ãĤ¿
    -0.14
    Arena
    -0.14
    obbled
    -0.14
    TypeInfo
    -0.14
     Opr
    -0.13
    RootElement
    -0.13
    uin
    -0.13
     ì¦
    -0.13
    POSITIVE LOGITS
     ASM
    0.15
     hyp
    0.15
     Vand
    0.15
     Canter
    0.15
     dim
    0.14
    ä½į
    0.14
     Miss
    0.14
     underst
    0.14
    _miss
    0.14
    491
    0.14
    Activations Density 0.027%

    No Known Activations