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. 10-LLAMASCOPE-RES-32K
    6. 20584
    Prev
    Next
    INDEX
    Explanations

    concepts related to easy and affordable construction or DIY projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usion
    -0.17
    mans
    -0.16
    idor
    -0.16
     subt
    -0.16
    outil
    -0.15
    ãĥ³ãĥĨ
    -0.15
    sandbox
    -0.15
    تز
    -0.14
    моÑĢ
    -0.14
    ispiel
    -0.14
    POSITIVE LOGITS
    elden
    0.18
     simple
    0.17
    ittal
    0.16
    å»
    0.15
    äº
    0.15
    wap
    0.15
    629
    0.14
    éĢĨ
    0.14
    pher
    0.14
    illus
    0.14
    Activations Density 0.313%

    No Known Activations