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. 31-LLAMASCOPE-RES-32K
    6. 6322
    Prev
    Next
    INDEX
    Explanations

    XML or HTML tags and similar markup elements

    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
     
    -0.31
    ,
    -0.24
    Âł
    -0.23
     (
    -0.21
    1
    -0.21
    :
    -0.21
    2
    -0.20
    .
    -0.19
    3
    -0.19
    0
    -0.19
    POSITIVE LOGITS
    remarks
    0.37
    typeparam
    0.34
    returns
    0.32
    seealso
    0.31
    param
    0.28
    exception
    0.26
    inheritdoc
    0.25
     remarks
    0.24
    paramref
    0.23
    para
    0.22
    Activations Density 0.006%

    No Known Activations