INDEX

Explanations

occurrences of the word "in" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Campo

-0.16

pedo

-0.15

PCP

-0.14

adden

-0.14

ãĥĬãĥ¼

-0.14

ND

-0.14

Ð½Ð´

-0.14

 Donne

-0.13

 Islam

-0.13

Clo

-0.13

POSITIVE LOGITS

.Strings

0.18

rase

0.17

iaz

0.16

tel

0.16

_nsec

0.15

mdir

0.15

_usec

0.15

atta

0.15

alach

0.14

"user

0.14

Activations Density 0.050%

occurrences of the word "in" and its variations

No Comments

No Known Activations