© 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. 18-LLAMASCOPE-RES-32K
    11. 28028
    Prev
    Next
    INDEX
    Explanations

    specific date formats or structured numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skill
    -0.15
    ark
    -0.15
    oin
    -0.15
     Skill
    -0.14
    ero
    -0.14
    694
    -0.14
    skill
    -0.14
    ohen
    -0.13
    676
    -0.13
    ator
    -0.13
    POSITIVE LOGITS
    oyer
    0.18
    份
    0.17
    /msg
    0.16
     rele
    0.15
    ÑĥÑĢе
    0.15
    Bindable
    0.15
    ÏģÎŃ
    0.15
     tarihli
    0.14
     rá»Ŀi
    0.14
    .scalablytyped
    0.14
    Activations Density 0.031%

    No Known Activations