© 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. 16-LLAMASCOPE-RES-32K
    11. 6013
    Prev
    Next
    INDEX
    Explanations

    programming-related function calls and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roll
    -0.14
    Æ°Æ¡ng
    -0.14
    555
    -0.14
    upe
    -0.13
     LED
    -0.13
    Verse
    -0.13
    lemek
    -0.13
    еÑĢо
    -0.13
    mdl
    -0.13
     //</
    -0.13
    POSITIVE LOGITS
    (↵
    0.25
    )(↵
    0.21
    uger
    0.21
    (č↵
    0.20
     [↵
    0.20
    !(↵
    0.20
     (↵
    0.20
    ](↵
    0.19
    uhn
    0.17
    >(↵
    0.17
    Activations Density 0.232%

    No Known Activations