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. 2-LLAMASCOPE-RES-32K
    6. 25694
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to surfing activities and culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÙħÙĪ
    -0.16
    orian
    -0.15
    struments
    -0.15
    íĴĪ
    -0.15
    avou
    -0.14
    lm
    -0.14
     Autof
    -0.14
    eka
    -0.14
    _wr
    -0.14
    chan
    -0.14
    POSITIVE LOGITS
    åĿĬ
    0.16
    ROP
    0.16
     Becker
    0.15
    ropic
    0.15
    ushima
    0.14
    ua
    0.14
    UA
    0.14
    ember
    0.13
     kvinne
    0.13
     hva
    0.13
    Activations Density 0.009%

    No Known Activations