INDEX

Explanations

occurrences of the word "enter" and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ency

-0.17

eno

-0.15

aturas

-0.14

ë¹Ľ

-0.14

EN

-0.14

ghan

-0.14

 Cunning

-0.13

/at

-0.13

UBL

-0.13

venir

-0.13

POSITIVE LOGITS

prising

0.36

prises

0.28

 into

0.18

preneur

0.18

PRI

0.17

lude

0.17

prene

0.17

CriticalSection

0.16

sts

0.15

Activations Density 0.025%

occurrences of the word "enter" and its variants

No Comments

No Known Activations