© 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. 24-LLAMASCOPE-RES-32K
    11. 16293
    Prev
    Next
    INDEX
    Explanations

    details related to packing and organizing items for travel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sleeve
    -0.19
     Beard
    -0.19
     Sleeve
    -0.18
     sleeves
    -0.16
     Shirt
    -0.16
     vest
    -0.15
    berger
    -0.15
    shirt
    -0.15
    è¡£
    -0.15
     towels
    -0.15
    POSITIVE LOGITS
     shoes
    0.49
     shoe
    0.45
     footwear
    0.44
     Shoes
    0.43
     boots
    0.43
     boot
    0.40
    éŀĭ
    0.40
     sandals
    0.38
     Shoe
    0.37
     sneakers
    0.37
    Activations Density 0.170%

    No Known Activations