INDEX

Explanations

mentions of fellowships and related terms indicating academic or professional affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

emoc

-0.17

gil

-0.16

erah

-0.16

okers

-0.16

ÑĥÐ»Ð¸

-0.15

ÐºÐ¾Ð·

-0.15

 meis

-0.14

ulp

-0.14

erne

-0.14

ilian

-0.14

POSITIVE LOGITS

ships

0.33

ship

0.21

shipping

0.21

hood

0.19

SHIP

0.18

hip

0.17

chaft

0.16

hips

0.16

ÙħØ§Ø±

0.16

iesen

0.15

Activations Density 0.007%

mentions of fellowships and related terms indicating academic or professional affiliations

No Comments

No Known Activations