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. 16-LLAMASCOPE-RES-32K
    6. 6492
    Prev
    Next
    INDEX
    Explanations

    phrases and titles with strong emotional themes and elements of storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alement
    -0.18
    iceps
    -0.16
    esty
    -0.15
    ABCDEFGHIJKLMNOP
    -0.14
    gom
    -0.14
    protocols
    -0.14
    taire
    -0.14
    Successfully
    -0.14
    Pairs
    -0.14
     سÙĪÙħ
    -0.14
    POSITIVE LOGITS
     Irma
    0.14
    arb
    0.14
    edd
    0.14
    ัà¸Ķ
    0.13
     Eden
    0.13
    ãĥ¼ãĤ¯
    0.13
    æŁ³
    0.13
     Habit
    0.13
    oted
    0.13
    che
    0.13
    Activations Density 0.182%

    No Known Activations