INDEX

Explanations

occurrences of the word "reveal" and its derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

anim

-0.16

iff

-0.15

 gelmiÅŁ

-0.15

iffin

-0.15

erre

-0.15

ify

-0.14

chu

-0.14

::$

-0.14

avanaugh

-0.14

POSITIVE LOGITS

aled

0.33

aling

0.23

olution

0.23

als

0.22

ILLE

0.20

ãĥ¥ãĥ¼

0.20

ille

0.19

aler

0.18

IEWS

0.18

aged

0.17

Activations Density 0.003%

occurrences of the word "reveal" and its derivatives

No Comments

No Known Activations