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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-LLAMASCOPE-RES-32K
    6. 23248
    Prev
    Next
    INDEX
    Explanations

    references to obituaries and announcements of passing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     å·
    -0.15
     Roberts
    -0.15
    ur
    -0.15
    364
    -0.14
    çļ
    -0.14
    hel
    -0.14
    adle
    -0.14
    get
    -0.13
    ôm
    -0.13
    ri
    -0.13
    POSITIVE LOGITS
    peria
    0.17
    istrovstvÃŃ
    0.16
    itti
    0.15
    uide
    0.15
    pheres
    0.15
    ilde
    0.15
    .scalablytyped
    0.14
    ILA
    0.14
    TestCategory
    0.14
    IData
    0.14
    Activations Density 0.037%

    No Known Activations