© 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. 5-LLAMASCOPE-RES-32K
    11. 481
    Prev
    Next
    INDEX
    Explanations

    punctuations, particularly commas and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urch
    -0.15
    é¼
    -0.15
    ntax
    -0.14
    irt
    -0.14
    ENSE
    -0.14
    éĽĦ
    -0.13
    åĪ¥
    -0.13
    -Ñı
    -0.13
     Gin
    -0.13
    Ta
    -0.13
    POSITIVE LOGITS
    clin
    0.17
    694
    0.16
    kle
    0.15
    _helpers
    0.14
    .Throw
    0.14
    جاد
    0.13
     Kraj
    0.13
     Roz
    0.13
    erialized
    0.13
    ersist
    0.13
    Activations Density 0.074%

    No Known Activations