INDEX

Explanations

the phrase "that's" or other variations related to affirmation or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 tento

-0.13

 Ulus

-0.13

 áº¥y

-0.13

 thereof

-0.13

erer

-0.13

ursive

-0.12

 evils

-0.12

æ²ĥ

-0.12

/non

-0.12

 ráº±ng

-0.12

POSITIVE LOGITS

why

0.38

how

0.33

 where

0.31

 what

0.27

 exactly

0.26

 precisely

0.26

why

0.26

 when

0.24

it

0.24

 assuming

0.23

Activations Density 0.087%

the phrase "that's" or other variations related to affirmation or emphasis

No Comments

No Known Activations