INDEX

Explanations

references to taste experiences and food enjoyment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

itaire

-0.20

erable

-0.19

istani

-0.18

nee

-0.17

ity

-0.17

ally

-0.17

utow

-0.17

ffset

-0.16

ller

-0.16

ised

-0.16

POSITIVE LOGITS

 buds

0.41

bud

0.35

Bud

0.30

bud

0.28

/sm

0.26

lessly

0.23

-test

0.21

eful

0.21

efully

0.21

ful

0.21

Activations Density 0.018%

references to taste experiences and food enjoyment

No Comments

No Known Activations