INDEX

Explanations

references to relocation and moving objects or properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

hole

-0.17

'gc

-0.15

wyn

-0.15

eways

-0.15

efe

-0.15

 hole

-0.14

eview

-0.14

ITS

-0.14

cke

-0.14

hani

-0.14

POSITIVE LOGITS

.Framework

0.18

uby

0.17

tit

0.15

pace

0.14

INGER

0.14

ymb

0.14

inge

0.14

uze

0.14

ique

0.14

oid

0.14

Activations Density 0.316%

references to relocation and moving objects or properties

No Comments

No Known Activations