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. 16-LLAMASCOPE-RES-32K
    6. 8458
    Prev
    Next
    INDEX
    Explanations

    key terms related to community resources and support systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.23
     
    -0.19
     "
    -0.18
    (
    -0.18
    yas
    -0.16
    feld
    -0.15
    pty
    -0.15
     And
    -0.15
     artificial
    -0.15
    eyed
    -0.15
    POSITIVE LOGITS
    .Encoding
    0.17
    ระ
    0.16
    vyk
    0.15
    endir
    0.15
    εί
    0.15
    516
    0.15
    _By
    0.15
    /interfaces
    0.15
    (parseFloat
    0.15
    /GPL
    0.14
    Activations Density 0.323%

    No Known Activations