INDEX

Explanations

questions that express curiosity or skepticism

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

appen

-0.16

æ¦

-0.15

aran

-0.15

ibles

-0.14

Ã¡mara

-0.13

CUS

-0.13

 ÙĪØ§Øª

-0.13

ypy

-0.13

mw

-0.13

amente

-0.13

POSITIVE LOGITS

ERSHEY

0.18

why

0.17

why

0.16

ä»ĭ

0.15

itt

0.14

 pourquoi

0.14

ÏĦÎ¹Îº

0.14

lom

0.14

assa

0.14

ymm

0.13

Activations Density 0.027%

questions that express curiosity or skepticism

No Comments

No Known Activations