INDEX

Explanations

repeated instances of the word "was" 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 @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

iem

-0.17

hiba

-0.15

nal

-0.15

vailability

-0.14

etter

-0.14

bservable

-0.14

oen

-0.14

iom

-0.13

adele

-0.13

now

-0.13

POSITIVE LOGITS

nt

0.21

 originally

0.19

/is

0.18

origin

0.17

Ä±

0.15

abi

0.15

orderid

0.14

ÙĨ

0.14

ãĤĬ

0.14

enville

0.14

Activations Density 0.301%

repeated instances of the word "was" in various contexts

No Comments

No Known Activations