INDEX

Explanations

terms related to brewing and breweries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

à¸ģ

-0.18

uteur

-0.15

ples

-0.15

cie

-0.15

otope

-0.15

odes

-0.14

chine

-0.14

 Ð¿ÑĢÐ¾Ð¶

-0.14

 NDEBUG

-0.14

urance

-0.14

POSITIVE LOGITS

eries

0.25

ERY

0.22

ery

0.21

ers

0.19

ster

0.19

erse

0.17

eres

0.17

ski

0.16

emed

0.16

pub

0.16

Activations Density 0.020%

terms related to brewing and breweries

No Comments

No Known Activations