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. 22-LLAMASCOPE-RES-32K
    6. 28274
    Prev
    Next
    INDEX
    Explanations

    technical processes and their related steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ertia
    -0.15
    urse
    -0.14
    apus
    -0.14
     yans
    -0.14
    ude
    -0.14
     strokeLine
    -0.14
    ãĥ«ãĥĪ
    -0.14
    cope
    -0.13
    oud
    -0.13
    apse
    -0.13
    POSITIVE LOGITS
     simply
    0.30
     basically
    0.28
     Simply
    0.25
     take
    0.25
     first
    0.23
    ãģ¾ãģļ
    0.23
     essentially
    0.23
    Simply
    0.22
     takes
    0.22
     Basically
    0.21
    Activations Density 0.301%

    No Known Activations