INDEX

Explanations

phrases that denote rankings or accolades regarding individuals or entities in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ataire

-0.16

nement

-0.16

sil

-0.15

 Fork

-0.15

agram

-0.15

_warn

-0.14

 forks

-0.14

Ð¸ÑģÑģ

-0.14

udios

-0.14

unny

-0.13

POSITIVE LOGITS

illi

0.16

Ð¶Ð¸Ð²

0.15

Ľ°

0.14

 PRES

0.14

è¿ŀ

0.14

 prest

0.14

seg

0.14

å¼

0.14

Pocket

0.14

cle

0.13

Activations Density 0.083%

phrases that denote rankings or accolades regarding individuals or entities in various fields

No Comments

No Known Activations