INDEX

Explanations

terms related to unique identification or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ertura

-0.16

å´

-0.14

urr

-0.14

ierarchy

-0.14

dez

-0.14

Fr

-0.14

Ã¡Å¾e

-0.13

 seedu

-0.13

 Koch

-0.13

 Kent

-0.13

POSITIVE LOGITS

ìĤ¬íķŃ

0.19

Ð°ÑĤÐµÐ»ÑĮÐ½Ð¾

0.18

 ìĤ¬íķŃ

0.17

eting

0.16

Ð°ÑĤÐµÐ»ÑĮ

0.16

 remark

0.15

atrix

0.15

ÑĮÑı

0.15

 ëĭ¤ìļ´ë°Ľ

0.15

Ð¾ÑģÑĥÐ´

0.14

Activations Density 0.005%

terms related to unique identification or classifications

No Comments

No Known Activations