INDEX

Explanations

details related to events and conditions, particularly in legal or disaster contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

amat

-0.18

mpi

-0.15

eson

-0.14

.mj

-0.14

bserv

-0.13

Ä±ndaki

-0.13

Î»Î»Î¬

-0.13

ToBounds

-0.13

 Ð½ÐµÐ´ÐµÐ»

-0.13

POSITIVE LOGITS

 with

0.17

 imaginable

0.16

0.15

,st

0.14

 knowing

0.14

_finalize

0.14

Cay

0.14

.Must

0.14

asil

0.14

,en

0.14

Activations Density 0.060%

details related to events and conditions, particularly in legal or disaster contexts

No Comments

No Known Activations