INDEX

Explanations

terms related to decision-making and evaluation processes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

letcher

-0.16

 ArrayCollection

-0.14

Ð¾Ð´Ñĥ

-0.14

agal

-0.13

irsch

-0.13

 whereas

-0.13

ns

-0.13

actly

-0.13

iece

-0.13

asy

-0.13

POSITIVE LOGITS

æ¬¡

0.15

Ð¾ÑģÑĮ

0.15

_nth

0.14

 dÃ¡n

0.14

MMdd

0.14

ç´

0.14

uvian

0.14

 æ¬¡

0.14

ãĥĥ

0.14

iest

0.14

Activations Density 0.295%

terms related to decision-making and evaluation processes

No Known Activations