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. 14-LLAMASCOPE-RES-32K
    6. 12610
    Prev
    Next
    INDEX
    Explanations

    references to games, films, and creative works, particularly in the context of enjoyment or value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iosa
    -0.15
    YYY
    -0.15
    vero
    -0.15
    lich
    -0.14
    IENT
    -0.14
    engkap
    -0.14
    581
    -0.14
    asing
    -0.13
     Lanc
    -0.13
    conto
    -0.13
    POSITIVE LOGITS
     Haram
    0.14
    wright
    0.14
    éĽ
    0.13
     Zaman
    0.13
    xeb
    0.13
    _lifetime
    0.13
     íĴ
    0.13
    matic
    0.13
    ateria
    0.13
    nie
    0.13
    Activations Density 0.572%

    No Known Activations