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. 27-LLAMASCOPE-RES-32K
    6. 1786
    Prev
    Next
    INDEX
    Explanations

    familial relationships and lineage details

    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
    Ðĭ
    -0.18
    /goto
    -0.15
    ảng
    -0.15
    conti
    -0.15
    Chip
    -0.15
    icho
    -0.15
    à¥ĩब
    -0.14
    bridge
    -0.14
    ģn
    -0.14
    Kate
    -0.14
    POSITIVE LOGITS
     Ver
    0.19
     Merlin
    0.19
     Vir
    0.18
     Darwin
    0.18
     Du
    0.18
     rural
    0.18
     Vern
    0.18
     Wayne
    0.17
     OP
    0.17
     Wesley
    0.17
    Activations Density 0.054%

    No Known Activations