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. 28-LLAMASCOPE-RES-32K
    6. 21013
    Prev
    Next
    INDEX
    Explanations

    information related to music releases and promotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esco
    -0.16
     excellent
    -0.16
    ponsored
    -0.15
     leider
    -0.14
     competent
    -0.14
    oton
    -0.14
    Networking
    -0.14
    itted
    -0.14
    olumn
    -0.14
     excell
    -0.14
    POSITIVE LOGITS
     bible
    0.16
    ifecycle
    0.15
    (strip
    0.14
    _CTRL
    0.14
    hel
    0.14
     ï
    0.13
    viso
    0.13
    /WebAPI
    0.13
    (Filter
    0.13
    adium
    0.13
    Activations Density 0.065%

    No Known Activations