INDEX

Explanations

instances of the phrase "I do" 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.18

Ø§ÛĮÙĩ

-0.18

doing

-0.17

ness

-0.17

noon

-0.17

nt

-0.17

ature

-0.16

pher

-0.16

gr

-0.16

sterol

-0.15

POSITIVE LOGITS

zed

0.22

ÂŃing

0.21

zen

0.21

ings

0.21

(es

0.21

xor

0.20

yles

0.20

able

0.20

ctr

0.20

led

0.19

Activations Density 0.045%

instances of the phrase "I do" in various contexts

No Comments

No Known Activations