INDEX

Explanations

references to the letter 'g' or words starting with 'g'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.21

et

-0.19

etri

-0.17

hb

-0.17

Î½Ïī

-0.17

Ð¾ÑĢÐ¾Ð´

-0.17

enz

-0.16

gross

-0.16

uum

-0.16

POSITIVE LOGITS

reek

0.21

0.20

ales

0.19

at

0.18

libc

0.17

arrison

0.17

ird

0.17

pf

0.17

esis

0.17

Activations Density 0.038%

references to the letter 'g' or words starting with 'g'

No Comments

No Known Activations