INDEX

Explanations

phrases expressing limitations or challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

oler

-0.18

eru

-0.17

pector

-0.16

ustin

-0.16

erman

-0.15

uitka

-0.14

Ã¼gen

-0.14

.ie

-0.14

inp

-0.13

Nim

-0.13

POSITIVE LOGITS

kaar

0.16

IMA

0.15

çĸ¾

0.15

 begr

0.14

eni

0.14

-detail

0.14

 detail

0.14

 smallest

0.14

Byte

0.14

iddy

0.14

Activations Density 0.144%

phrases expressing limitations or challenges

No Comments

No Known Activations