INDEX

Explanations

important nouns and concepts related to identification and categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ìĬĪ

-0.17

anean

-0.16

_arr

-0.16

 Fior

-0.16

anship

-0.15

_ASM

-0.15

AREN

-0.15

.twimg

-0.15

elow

-0.15

abase

-0.15

POSITIVE LOGITS

din

0.16

SYS

0.16

/sys

0.16

 ÙĨÙĤØ¯

0.16

ema

0.15

sn

0.15

olin

0.15

 Katz

0.15

 audi

0.15

ist

0.15

Activations Density 0.022%

important nouns and concepts related to identification and categorization

No Comments

No Known Activations