INDEX

Explanations

references to programming concepts and libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

brero

-0.16

otto

-0.15

rof

-0.15

vo

-0.15

enario

-0.15

Visitor

-0.15

VO

-0.14

kening

-0.14

aire

-0.14

erot

-0.14

POSITIVE LOGITS

avigator

0.15

Î½Ïī

0.14

ioctl

0.14

ichert

0.14

TZ

0.14

iscard

0.14

_cmos

0.14

aint

0.14

outu

0.13

ismatch

0.13

Activations Density 0.045%

references to programming concepts and libraries

No Comments

No Known Activations