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. 15-LLAMASCOPE-RES-32K
    6. 18891
    Prev
    Next
    INDEX
    Explanations

    timestamps and publication dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rue
    -0.15
    ARS
    -0.15
    ãģ®ãĤĤ
    -0.14
    /Typography
    -0.14
    ards
    -0.14
    arton
    -0.13
     monthly
    -0.13
    ":[{↵
    -0.13
    erate
    -0.13
    457
    -0.13
    POSITIVE LOGITS
    .scalablytyped
    0.19
    aisy
    0.19
    ollen
    0.15
    ym
    0.15
    ymous
    0.14
    ict
    0.14
    pais
    0.14
    unken
    0.14
     defaultCenter
    0.13
    hsi
    0.13
    Activations Density 0.028%

    No Known Activations