INDEX

Explanations

adjectives that describe quantity or size

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

statt

-0.17

OOM

-0.14

imd

-0.14

inski

-0.14

á»ĵi

-0.13

 scarc

-0.13

dims

-0.13

otti

-0.13

ure

-0.12

 guise

-0.12

POSITIVE LOGITS

 amount

0.59

 portion

0.48

 number

0.48

amount

0.46

 amounts

0.41

 Amount

0.39

 proportion

0.38

portion

0.37

 portions

0.37

number

0.36

Activations Density 0.123%

adjectives that describe quantity or size

No Comments

No Known Activations