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. 7-LLAMASCOPE-RES-32K
    6. 7890
    Prev
    Next
    INDEX
    Explanations

    names of programs and initiatives related to education and professional certification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fbe
    -0.16
    aus
    -0.15
    .Sdk
    -0.15
    rees
    -0.15
    ething
    -0.14
    's
    -0.14
    pedia
    -0.14
     minim
    -0.14
    atra
    -0.13
    allen
    -0.13
    POSITIVE LOGITS
    /Peak
    0.15
    ordinator
    0.15
    GenerationStrategy
    0.15
    orem
    0.15
    ää
    0.14
    /Sub
    0.14
    /Instruction
    0.14
    âĦ¢
    0.14
    HeaderCode
    0.14
    OffsetTable
    0.13
    Activations Density 0.352%

    No Known Activations