INDEX

Explanations

phrases indicating the presence of guests or visitors in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

Ð±Ð¾Ð»

-0.16

onders

-0.15

zon

-0.14

 Heard

-0.14

iger

-0.13

oked

-0.13

.MixedReality

-0.13

monic

-0.13

_DX

-0.13

otre

-0.13

POSITIVE LOGITS

 treated

0.41

 greeted

0.34

 treat

0.32

met

0.32

gre

0.26

-treated

0.25

 priv

0.25

 treats

0.24

 Treat

0.24

 trat

0.23

Activations Density 0.091%

phrases indicating the presence of guests or visitors in various contexts

No Comments

No Known Activations