INDEX

Explanations

instances of the word "will" in various forms to indicate future actions or predictions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

illez

-0.17

ellar

-0.15

elf

-0.15

uelles

-0.14

å¼Ł

-0.14

ÑģÑĤÐ¸

-0.14

 SELF

-0.13

uf

-0.13

ssize

-0.13

uvre

-0.13

POSITIVE LOGITS

lier

0.16

à¤¦à¤°

0.15

omi

0.15

itmap

0.15

 Transit

0.14

 Boeh

0.14

APO

0.14

rosso

0.14

 transit

0.13

Dix

0.13

Activations Density 0.073%

instances of the word "will" in various forms to indicate future actions or predictions

No Comments

No Known Activations