INDEX

Explanations

diverse references to food and cooking-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Ã©al

-0.16

íĶ½

-0.15

WithString

-0.15

ÐµÑĤÐµÐ»ÑĮ

-0.15

Ã¦nd

-0.15

imet

-0.15

IXEL

-0.14

peater

-0.14

EEE

-0.14

undy

-0.14

POSITIVE LOGITS

ucson

0.17

gether

0.17

ting

0.17

mania

0.16

imestep

0.16

istic

0.16

ologies

0.16

Ð±Ð¾ÑĢ

0.16

ell

0.15

fall

0.15

Activations Density 0.499%

diverse references to food and cooking-related terms

No Comments

No Known Activations