INDEX

Explanations

names and references related to entities and configurations in technical content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

yne

-0.17

icode

-0.17

oku

-0.16

 Aires

-0.15

olic

-0.15

yer

-0.14

ocal

-0.14

ÐµÐ³Ð°

-0.14

atos

-0.14

Ã¤h

-0.14

POSITIVE LOGITS

ondon

0.16

ASIC

0.15

rink

0.15

à¸¶

0.15

RTOS

0.14

 tisk

0.14

 vÃŃ

0.14

 sáºµn

0.14

rava

0.14

(CharSequence

0.13

Activations Density 0.005%

names and references related to entities and configurations in technical content

No Comments

No Known Activations