INDEX

Explanations

instances of the word "much"

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

onda

-0.17

axter

-0.16

nier

-0.16

ãĤ¯ãĤ»

-0.15

Ø¨ÙĦØº

-0.15

entina

-0.14

Ú¯Ø±

-0.14

viar

-0.14

Ãºn

-0.14

 Ð¾ÑĤÐ¿

-0.14

POSITIVE LOGITS

ubb

0.15

lep

0.15

losed

0.14

 Jelly

0.14

EIF

0.14

 Injectable

0.14

UPLE

0.14

Î±Î¹Î½

0.14

apro

0.14

 Bernstein

0.13

Activations Density 0.006%

instances of the word "much"

No Comments

No Known Activations