INDEX

Explanations

references to sweetness, particularly in food or culinary contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

aised

-0.17

asco

-0.16

caffold

-0.15

quo

-0.15

OUS

-0.15

Ø¯Ø§Ø¯

-0.15

BST

-0.15

ynthesis

-0.15

atische

-0.15

hlen

-0.14

POSITIVE LOGITS

ened

0.45

eners

0.43

ener

0.42

ening

0.40

est

0.38

ie

0.34

heart

0.32

he

0.31

ens

0.30

grass

0.28

Activations Density 0.018%

references to sweetness, particularly in food or culinary contexts

No Comments

No Known Activations