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. 12-LLAMASCOPE-RES-32K
    6. 5847
    Prev
    Next
    INDEX
    Explanations

    terms related to academic research and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Route
    -0.14
     Revel
    -0.13
    иÑĩно
    -0.13
    ureau
    -0.13
    ATO
    -0.13
    ÑĢел
    -0.13
    agas
    -0.13
    Äįást
    -0.13
    stud
    -0.12
    asons
    -0.12
    POSITIVE LOGITS
    raquo
    0.16
    /Dk
    0.14
    dea
    0.14
    osten
    0.14
    ankan
    0.14
    hw
    0.14
    ertia
    0.13
     ger
    0.13
    /goto
    0.13
     proven
    0.13
    Activations Density 0.007%

    No Known Activations