INDEX

Explanations

references to death or dying

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

íĺķ

-0.16

weise

-0.16

ial

-0.16

xt

-0.15

ettings

-0.15

.fac

-0.15

adera

-0.15

SSION

-0.14

mesinin

-0.14

ationale

-0.14

POSITIVE LOGITS

ened

0.21

ening

0.20

beat

0.20

rice

0.18

iker

0.17

oppel

0.16

roe

0.16

stock

0.16

locked

0.16

Activations Density 0.014%

references to death or dying

No Comments

No Known Activations