INDEX

Explanations

references to wax-related products or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

mise

-0.17

reece

-0.17

çłģ

-0.16

aise

-0.15

erval

-0.15

Insp

-0.15

liness

-0.14

rest

-0.14

ceipt

-0.14

udes

-0.14

POSITIVE LOGITS

wax

0.20

 candle

0.18

Wax

0.18

 candles

0.18

-paper

0.18

upported

0.17

 Candle

0.17

pected

0.17

wing

0.16

xy

0.16

Activations Density 0.005%

references to wax-related products or processes

No Comments

No Known Activations