INDEX

Explanations

programming or code-related concepts and utility functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

tery

-0.16

attery

-0.15

etin

-0.14

éĥ¨å±ĭ

-0.14

/archive

-0.14

 Streams

-0.13

teb

-0.13

terr

-0.13

itol

-0.13

 Dudley

-0.13

POSITIVE LOGITS

/../

0.15

_CAST

0.15

æĹıèĩªæ²»

0.14

ä¹±

0.14

ãģ¯ãģļ

0.14

strstr

0.13

_cast

0.12

.newArrayList

0.12

isten

0.12

SharedPtr

0.12

Activations Density 0.128%

programming or code-related concepts and utility functions

No Comments

No Known Activations