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. 24-LLAMASCOPE-RES-32K
    6. 18067
    Prev
    Next
    INDEX
    Explanations

    references to collaborative efforts and the role of individuals in achieving tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Amend
    -0.15
    麻
    -0.14
    Upgrade
    -0.14
     ---------------------------------------------------------------------------↵
    -0.14
    ,...↵↵
    -0.13
     resort
    -0.13
    :eq
    -0.13
    659
    -0.13
     devis
    -0.13
    ador
    -0.13
    POSITIVE LOGITS
     execution
    0.23
     executing
    0.21
     implementation
    0.20
    .execute
    0.20
     execute
    0.20
     Execution
    0.20
    execution
    0.20
    Implementation
    0.19
     bring
    0.19
     conception
    0.19
    Activations Density 0.193%

    No Known Activations