INDEX

Explanations

references to personal experiences and travel narratives

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

fat

-0.15

 Wind

-0.15

 wind

-0.15

ither

-0.15

fat

-0.15

åłĤ

-0.14

okud

-0.14

 pret

-0.14

 Korean

-0.14

POSITIVE LOGITS

.gf

0.16

eler

0.14

Ø§ÙĤ

0.14

ÑĢÑĥÐ³

0.14

dek

0.14

mdi

0.13

dera

0.13

acts

0.13

lev

0.13

 Backpack

0.13

Activations Density 0.069%

references to personal experiences and travel narratives

No Comments

No Known Activations