INDEX

Explanations

function and method definitions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

_UNUSED

-0.15

etwork

-0.15

.ham

-0.13

ÙĦØ§ØŃ

-0.13

pron

-0.13

ibel

-0.13

phans

-0.13

 ëĦ¤ìĿ´íĬ¸

-0.13

iew

-0.12

bery

-0.12

POSITIVE LOGITS

adays

0.24

odore

0.22

atre

0.19

anmar

0.18

strument

0.16

etheless

0.16

ingleton

0.15

ward

0.15

struments

0.15

Activations Density 0.370%

function and method definitions in code

No Comments

No Known Activations