© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 10-LLAMASCOPE-RES-32K
    6. 13598
    Prev
    Next
    INDEX
    Explanations

    references to weight loss and related strategies

    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
    ipsis
    -0.17
    ey
    -0.16
    itary
    -0.14
    ANTLR
    -0.14
    ilers
    -0.14
    alic
    -0.13
    uclear
    -0.13
    eyed
    -0.13
    .getTarget
    -0.13
    çķª
    -0.13
    POSITIVE LOGITS
    abwe
    0.15
    hel
    0.15
    /fixtures
    0.14
    antino
    0.14
    inha
    0.14
    ãĥ¼ãĥª
    0.14
    BufferData
    0.14
    unload
    0.14
     nuest
    0.13
    activex
    0.13
    Activations Density 0.306%

    No Known Activations