INDEX

Explanations

instances of the letter "O" in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

rire

-0.15

bat

-0.15

 ç´

-0.15

utas

-0.14

assi

-0.14

ABI

-0.14

 Hague

-0.14

nze

-0.14

ynamo

-0.14

fried

-0.14

POSITIVE LOGITS

linger

0.17

ehr

0.16

iola

0.16

lander

0.15

DOT

0.15

cala

0.15

pled

0.14

awah

0.14

 darken

0.14

 Canada

0.14

Activations Density 0.040%

instances of the letter "O" in text

No Comments

No Known Activations