INDEX

Explanations

the repetition of the word "do" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

fy

-0.16

cular

-0.15

innen

-0.15

stoup

-0.14

stras

-0.14

.parseFloat

-0.14

meer

-0.14

neas

-0.14

rox

-0.14

ency

-0.14

POSITIVE LOGITS

cket

0.20

Ã±ana

0.17

ze

0.15

ork

0.15

inky

0.14

berman

0.14

xygen

0.14

actic

0.14

lesi

0.14

0.13

Activations Density 0.107%

the repetition of the word "do" and its variations in various contexts

No Comments

No Known Activations