INDEX

Explanations

instances of the word "inscribed."

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

eva

-0.21

eum

-0.18

ulin

-0.17

hong

-0.17

omnia

-0.17

IGHT

-0.17

ty

-0.16

hausen

-0.16

ema

-0.16

POSITIVE LOGITS

cribed

0.28

criptions

0.25

pite

0.23

pects

0.22

cribe

0.22

cript

0.22

cribing

0.21

istent

0.21

cribes

0.20

olvency

0.20

Activations Density 0.007%

instances of the word "inscribed."

No Comments

No Known Activations