INDEX

Explanations

terms related to foot and leg support or equipment features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

åı£

-0.20

 Mouth

-0.19

 throat

-0.19

åĶĩ

-0.18

ahat

-0.18

 mouth

-0.18

 Neck

-0.18

å¸½

-0.17

 beard

-0.17

neck

-0.17

POSITIVE LOGITS

leg

0.47

-leg

0.42

 legs

0.41

leg

0.41

 feet

0.38

Leg

0.38

 foot

0.38

Leg

0.37

LEG

0.35

LEG

0.34

Activations Density 0.152%

terms related to foot and leg support or equipment features

No Comments

No Known Activations