INDEX

Explanations

abbreviations or acronyms related to organizations or terms in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

UCKET

-0.17

unt

-0.14

agar

-0.14

Ã¡nt

-0.14

ient

-0.14

YN

-0.14

uer

-0.13

ft

-0.13

unct

-0.13

POSITIVE LOGITS

otec

0.20

erin

0.18

adal

0.17

.bz

0.16

à¸·à¹Ī

0.14

yat

0.14

_rsp

0.13

 Wagner

0.13

arta

0.13

Activations Density 0.232%

abbreviations or acronyms related to organizations or terms in various contexts

No Comments

No Known Activations