INDEX

Explanations

specific terms and phrases related to programming and technical discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

.platform

-0.17

çĤ®

-0.15

entionPolicy

-0.15

Ã«

-0.14

stroy

-0.14

_compat

-0.14

onaut

-0.14

ngrx

-0.13

SYS

-0.13

anut

-0.13

POSITIVE LOGITS

 ÑģÐ¾Ñĩ

0.16

anje

0.15

 Vale

0.15

 Morr

0.14

>>↵↵

0.14

iel

0.13

lien

0.13

 impressions

0.13

Zem

0.13

ÑģÐ¾ÑĤ

0.13

Activations Density 0.000%

specific terms and phrases related to programming and technical discussions

No Comments

No Known Activations