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. 31-LLAMASCOPE-RES-32K
    6. 6732
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure, particularly in relation to code functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ãī
    -0.46
     Et
    -0.45
     Es
    -0.44
     Eg
    -0.43
     Eb
    -0.43
    /E
    -0.43
    -E
    -0.42
     Ez
    -0.42
    (E
    -0.42
     Ea
    -0.42
    POSITIVE LOGITS
    à§ĩ
    0.12
    xAD
    0.11
    Ïĩν
    0.11
     Kurul
    0.11
    /browse
    0.11
    xAF
    0.11
    xAC
    0.11
    ãģĪ
    0.11
    Matchers
    0.10
     Names
    0.10
    Activations Density 0.137%

    No Known Activations