INDEX

Explanations

specific named entities, particularly proper nouns and significant numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

otton

-0.16

berger

-0.16

 adipiscing

-0.15

Animating

-0.14

 circum

-0.14

ìĻĦ

-0.14

plet

-0.14

ets

-0.14

POSITIVE LOGITS

hyper

0.19

Hyper

0.19

ÙĩØ§Ø±

0.17

 Hyper

0.17

 hyper

0.17

HY

0.16

kÃ¼

0.16

/browser

0.15

agine

0.15

bestos

0.15

Activations Density 0.018%

specific named entities, particularly proper nouns and significant numerical values

No Comments

No Known Activations