INDEX

Explanations

references to community initiatives and collaborative efforts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ave

-0.16

ama

-0.14

 tuto

-0.13

actable

-0.13

 unrelated

-0.13

hausen

-0.13

Ø¶

-0.13

-0.12

 Shadows

-0.12

POSITIVE LOGITS

 ours

0.32

 locally

0.26

 local

0.25

local

0.23

 here

0.21

 Ð»Ð¾Ðº

0.20

 HERE

0.20

 LOCAL

0.20

our

0.20

 localize

0.19

Activations Density 0.333%

references to community initiatives and collaborative efforts

No Comments

No Known Activations