Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 17627
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mult
    -0.15
     later
    -0.15
     wives
    -0.15
     marginal
    -0.14
     proto
    -0.14
    son
    -0.14
     spouses
    -0.14
    üm
    -0.14
    ui
    -0.14
     https
    -0.14
    POSITIVE LOGITS
     Recovery
    0.19
    /english
    0.17
     recovery
    0.16
    ictionary
    0.15
     Recover
    0.15
    ´ij
    0.15
     fkk
    0.14
    _recovery
    0.14
    aravel
    0.14
     advoc
    0.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.