© 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. 31-LLAMASCOPE-RES-32K
    11. 10356
    Prev
    Next
    INDEX
    Explanations

    specific terms and concepts related to a particular organization or classification system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    иÑĩеÑģÑĤво
    -0.25
     erste
    -0.24
    stvo
    -0.23
     weitere
    -0.23
     дÑĢÑĥгие
    -0.22
    еÑĩение
    -0.22
     andere
    -0.21
     ÑĸнÑĪÑĸ
    -0.21
     neue
    -0.21
     verschiedene
    -0.21
    POSITIVE LOGITS
    ного
    0.40
    ового
    0.36
    Ñģкого
    0.35
    енного
    0.35
    ÑĪего
    0.34
    кого
    0.33
    алÑĮного
    0.33
    оÑĩного
    0.32
    ÑģÑĤвенного
    0.31
    иÑĤелÑĮного
    0.31
    Activations Density 0.053%

    No Known Activations