INDEX

Explanations

references to postcards and related items

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

gor

-0.15

 retro

-0.15

datal

-0.14

enor

-0.14

bin

-0.14

 Fare

-0.13

 talent

-0.13

vro

-0.13

Ø®ÙĪØ§Ø³Øª

-0.13

 qualified

-0.13

POSITIVE LOGITS

ieÅ¼

0.18

 ÑģÐ¼ÐµÑĢ

0.17

Ø±ÙĬØ·

0.17

iface

0.15

toi

0.15

å¼µ

0.15

ÙĬÙĪÙĨ

0.14

åħ¼

0.14

íĺ

0.13

chang

0.13

Activations Density 0.006%

references to postcards and related items

No Comments

No Known Activations