INDEX

Explanations

phrases that express confusion or disbelief

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

loff

-0.19

.strict

-0.17

berman

-0.17

nok

-0.16

ibbon

-0.15

ennon

-0.15

dling

-0.14

ALSE

-0.14

orning

-0.14

 Ulus

-0.14

POSITIVE LOGITS

heck

0.16

kontakte

0.15

 litter

0.14

 Memo

0.14

 exactly

0.14

fug

0.14

/start

0.14

 Mich

0.14

ivers

0.13

cas

0.13

Activations Density 0.161%

phrases that express confusion or disbelief

No Comments

No Known Activations