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. 27-LLAMASCOPE-RES-32K
    6. 11679
    Prev
    Next
    INDEX
    Explanations

    key terms related to processes and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emean
    -0.17
    ildo
    -0.15
     Poll
    -0.15
    orate
    -0.15
    anik
    -0.15
    оÑĢÑĸ
    -0.14
    _magic
    -0.14
    braco
    -0.14
     principle
    -0.14
    esub
    -0.14
    POSITIVE LOGITS
    -agent
    0.17
     Agent
    0.17
    Agent
    0.17
     agent
    0.16
    agent
    0.16
    .Agent
    0.16
    (agent
    0.15
    æĹı
    0.15
     numberOfRows
    0.15
    ĭ
    0.14
    Activations Density 0.014%

    No Known Activations