INDEX

Explanations

terms related to the processing, modification, and characteristics of various materials and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

quier

-0.16

rist

-0.14

éĢŁ

-0.14

inker

-0.14

merican

-0.14

otto

-0.14

_ASYNC

-0.13

 obce

-0.13

/framework

-0.13

oner

-0.13

POSITIVE LOGITS

 into

0.17

 using

0.16

 with

0.15

via

0.14

 according

0.14

to

0.14

so

0.14

ellation

0.14

ki

0.13

åħį

0.13

Activations Density 0.220%

terms related to the processing, modification, and characteristics of various materials and products

No Comments

No Known Activations