INDEX

Explanations

instances of the word "all" and its variations in different 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

ripp

-0.17

ÏĢÎ·

-0.16

oksen

-0.15

 DÃ¼n

-0.15

caled

-0.15

ãģķ

-0.14

pij

-0.14

-regexp

-0.14

POSITIVE LOGITS

 manner

0.20

sort

0.19

erdale

0.18

-round

0.18

bar

0.17

 credit

0.16

 weather

0.16

.weather

0.15

 eyes

0.15

ied

0.15

Activations Density 0.045%

instances of the word "all" and its variations in different contexts

No Comments

No Known Activations