INDEX

Explanations

references to spinal structures and injuries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

onas

-0.17

iki

-0.17

-Sah

-0.15

é¼»

-0.15

ucer

-0.15

ValuePair

-0.14

ellite

-0.14

akening

-0.14

aler

-0.14

oks

-0.14

POSITIVE LOGITS

 cord

0.53

 Cord

0.46

cord

0.42

 cords

0.34

CORD

0.32

 chord

0.29

 column

0.29

/column

0.26

column

0.25

 Column

0.25

Activations Density 0.005%

references to spinal structures and injuries

No Comments

No Known Activations