© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 16156
    Prev
    Next
    INDEX
    Explanations

    geographical and location-specific information related to studies or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achu
    -0.16
     Odin
    -0.15
     Utt
    -0.15
     Eston
    -0.15
    λÏĮ
    -0.14
    iola
    -0.14
     VÅ¡ech
    -0.14
     Tamil
    -0.14
    çĶ²
    -0.14
    452
    -0.14
    POSITIVE LOGITS
     Morocco
    0.51
     Moroccan
    0.49
    Mor
    0.48
     Mor
    0.41
     Marr
    0.39
     mor
    0.38
     Rab
    0.37
     MOR
    0.35
     Cas
    0.34
     اÙĦÙħغرب
    0.31
    Activations Density 0.045%

    No Known Activations