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. 24-LLAMASCOPE-RES-32K
    6. 19184
    Prev
    Next
    INDEX
    Explanations

    universal truths or concepts that apply to all beings or situations

    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
    ÑģÑı
    -0.17
    pec
    -0.16
     Peng
    -0.15
    887
    -0.14
    SelectedItem
    -0.14
    DOT
    -0.14
    151
    -0.14
    سÙĪ
    -0.14
    edu
    -0.14
    noch
    -0.13
    POSITIVE LOGITS
     manner
    0.19
     creation
    0.18
     else
    0.17
    odial
    0.17
     men
    0.17
    creation
    0.16
     Creation
    0.16
     knowledge
    0.16
     that
    0.16
    that
    0.15
    Activations Density 0.087%

    No Known Activations