INDEX

Explanations

specific names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

een

-0.16

 Lester

-0.16

est

-0.15

arlo

-0.15

_traits

-0.15

ioni

-0.15

ayo

-0.15

estar

-0.14

oni

-0.14

 Hayden

-0.14

POSITIVE LOGITS

isque

0.20

 <!--[

0.16

_NATIVE

0.16

pector

0.15

-native

0.14

.ManyToMany

0.14

à¹Ģà¸ł

0.14

oley

0.14

unj

0.14

 MouseEventArgs

0.14

Activations Density 0.601%

specific names and titles

No Comments

No Known Activations