INDEX

Explanations

discussions around problem-solving and troubleshooting in coding contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kest

-0.16

axy

-0.16

ungs

-0.15

ìĸĳ

-0.15

"),"

-0.14

akis

-0.14

Ã¤ÃŁ

-0.14

isel

-0.14

 Ãĩev

-0.14

Blockly

-0.13

POSITIVE LOGITS

ocre

0.16

Lab

0.14

lab

0.14

rocket

0.14

çį

0.14

 Advisory

0.13

iÃ¨res

0.13

 Laboratory

0.13

.lab

0.13

Activations Density 0.085%

discussions around problem-solving and troubleshooting in coding contexts

No Comments

No Known Activations