INDEX

Explanations

references to books and reading-related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ante

-0.18

gne

-0.15

GPC

-0.14

ickey

-0.14

antes

-0.14

Dys

-0.14

verages

-0.14

ulty

-0.14

 Duffy

-0.13

oner

-0.13

POSITIVE LOGITS

elian

0.17

Nat

0.17

Nat

0.15

NAN

0.15

istine

0.14

isko

0.14

ÄŁinin

0.14

osg

0.14

igers

0.13

 Troll

0.13

Activations Density 0.411%

references to books and reading-related activities

No Comments

No Known Activations

references to books and reading-related activities

No Comments

No Known Activations