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. 9-LLAMASCOPE-RES-32K
    6. 16404
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to data structures and analysis

    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
    èŀ
    -0.15
    egov
    -0.14
    lisi
    -0.14
    ÎĨ
    -0.14
    ADOR
    -0.13
    æ¢
    -0.13
    .opend
    -0.13
    scriptId
    -0.13
    iaux
    -0.13
    (es
    -0.13
    POSITIVE LOGITS
    TestFixture
    0.15
    ụy
    0.15
    PLL
    0.15
    alg
    0.14
    _callable
    0.14
    人æīį
    0.14
    FM
    0.14
    ZH
    0.13
    mlink
    0.13
    ahead
    0.13
    Activations Density 0.650%

    No Known Activations