INDEX

Explanations

concepts related to consumer advice and product qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

OVE

-0.15

ilst

-0.15

 Mehr

-0.15

entifier

-0.14

foon

-0.14

 Celt

-0.14

Ø±ÙĬØ¨

-0.14

aments

-0.13

 fidelity

-0.13

_Native

-0.13

POSITIVE LOGITS

 earn

0.28

 earning

0.26

earn

0.24

 earns

0.24

 earnings

0.23

-make

0.23

earned

0.23

earning

0.23

 make

0.22

 earned

0.22

Activations Density 0.023%

concepts related to consumer advice and product qualities

No Comments

No Known Activations