INDEX

Explanations

geographical locations and related terminology

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

 ####

-0.18

posted

-0.16

###

-0.16

anax

-0.15

##

-0.15

dech

-0.15

-comments

-0.14

clus

-0.14

StackTrace

-0.14

 posted

-0.14

POSITIVE LOGITS

Template

0.26

 Template

0.26

Coordinates

0.24

 Coordinates

0.24

{{{

0.23

Lua

0.23

Lua

0.21

{{{

0.20

 redirects

0.19

Redirect

0.19

Activations Density 0.031%

geographical locations and related terminology

No Comments

No Known Activations