INDEX

Explanations

phrases indicating numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ÃŃrk

-0.17

reopen

-0.16

isque

-0.15

;element

-0.14

AtPath

-0.14

deniz

-0.14

ibase

-0.14

rossover

-0.14

klad

-0.14

mazon

-0.14

POSITIVE LOGITS

0.16

zers

0.16

 Price

0.15

 retired

0.15

0.14

 unsub

0.14

 âĢ¦↵

0.14

âĢ¦↵

0.14

unf

0.14

Activations Density 0.201%

phrases indicating numerical data or statistics

No Comments

No Known Activations