INDEX

Explanations

references to the term "Western."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

anton

-0.19

nel

-0.19

allows

-0.16

loom

-0.16

turnstile

-0.15

-0.14

 Olson

-0.14

olar

-0.14

POSITIVE LOGITS

most

0.29

ized

0.26

 blot

0.24

ization

0.24

-most

0.23

ers

0.22

esse

0.21

ised

0.21

 Hemisphere

0.21

Activations Density 0.011%

references to the term "Western."

No Comments

No Known Activations