INDEX

Explanations

actions related to performance and participation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

/current

-0.15

wen

-0.15

wap

-0.14

/full

-0.14

ÑĳÑĢ

-0.14

ÑĤÐ°ÐºÐ¸

-0.14

/out

-0.14

tery

-0.13

rais

-0.13

jam

-0.13

POSITIVE LOGITS

Ĵáŀ

0.15

oulder

0.15

lrt

0.14

-lnd

0.14

incinn

0.14

erk

0.14

ailable

0.14

jsc

0.13

GuidId

0.13

emm

0.13

Activations Density 0.679%

actions related to performance and participation

No Comments

No Known Activations