INDEX

Explanations

references to biting or being bitten

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

rig

-0.18

ãģ£ãģ

-0.16

 voks

-0.15

hg

-0.15

.scalablytyped

-0.15

tober

-0.15

umber

-0.14

.normalize

-0.14

plementation

-0.14

Rig

-0.14

POSITIVE LOGITS

 UITableViewController

0.15

bite

0.15

zsche

0.14

itin

0.14

 Vita

0.14

arya

0.14

 Liberties

0.14

ITU

0.14

_numpy

0.13

elow

0.13

Activations Density 0.018%

references to biting or being bitten

No Comments

No Known Activations