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. 4-LLAMASCOPE-RES-32K
    6. 23555
    Prev
    Next
    INDEX
    Explanations

    technical terms related to server processes and system operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avern
    -0.17
    reira
    -0.14
    idot
    -0.14
    .ie
    -0.14
    çĦ
    -0.14
    467
    -0.13
    umann
    -0.13
    untu
    -0.13
    TemplateName
    -0.13
    icho
    -0.13
    POSITIVE LOGITS
    enor
    0.15
    jes
    0.15
     Aires
    0.15
    APPER
    0.14
     Gins
    0.14
    enso
    0.14
     UNIT
    0.14
    aye
    0.13
    Attachments
    0.13
    ja
    0.13
    Activations Density 0.070%

    No Known Activations