INDEX

Explanations

terms related to inspection and analysis processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

uchen

-0.16

olut

-0.16

ÐµÐ»Ñİ

-0.16

ÑģÐ¾Ð»

-0.15

kem

-0.15

Ð¶Ð°

-0.15

hea

-0.15

idge

-0.15

immel

-0.15

erva

-0.14

POSITIVE LOGITS

Ã¼Ã§Ã¼k

0.15

adas

0.15

å¯Ł

0.15

DEX

0.15

lobals

0.15

è¨ĢãģĦ

0.15

eing

0.14

 Adri

0.14

_rom

0.14

.codes

0.14

Activations Density 0.220%

terms related to inspection and analysis processes

No Comments

No Known Activations