INDEX

Explanations

proper nouns, particularly names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

plevel

-0.15

WEB

-0.15

Ã¢t

-0.14

(delegate

-0.14

 landfill

-0.14

ily

-0.14

anton

-0.14

prit

-0.14

dn

-0.13

angi

-0.13

POSITIVE LOGITS

ãĥ¶

0.16

ziaÅĤ

0.16

uil

0.16

 Ipsum

0.15

ESP

0.15

å¹

0.14

orie

0.14

 Guth

0.14

 Lair

0.14

yne

0.14

Activations Density 0.011%

proper nouns, particularly names and titles

No Comments

No Known Activations