INDEX

Explanations

references to escape and displacement

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

è¯ī

-0.17

addock

-0.15

rans

-0.14

è¨´

-0.14

setQuery

-0.14

éľ

-0.14

ÐĿÐŀ

-0.13

lei

-0.13

alleng

-0.13

aal

-0.13

POSITIVE LOGITS

eru

0.16

ordan

0.15

ÙĪÙĦÛĮ

0.15

.opend

0.15

orado

0.15

ess

0.14

ODB

0.14

anean

0.14

Ð»Ð°Ð³

0.14

asma

0.14

Activations Density 0.038%

references to escape and displacement

No Comments

No Known Activations