© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 18956
    Prev
    Next
    INDEX
    Explanations

    references to legal actions and financial implications related to institutions or organizations

    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
    mlin
    -0.18
    FFE
    -0.16
    ekk
    -0.15
    argon
    -0.15
    roc
    -0.15
     DDS
    -0.15
    ucene
    -0.15
    趣
    -0.14
     Ec
    -0.14
    STS
    -0.14
    POSITIVE LOGITS
     AC
    1.30
    AC
    1.13
    .AC
    0.90
    _AC
    0.88
     ACM
    0.71
     ACC
    0.69
     ACS
    0.63
     ac
    0.62
     ACE
    0.59
     ACA
    0.56
    Activations Density 0.030%

    No Known Activations