INDEX

Explanations

text that references or discusses records and official documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Ð¿ÐµÑĢ

-0.15

Ð¸Ð»Ñı

-0.15

avier

-0.15

áº§m

-0.15

elier

-0.14

 rollback

-0.14

rollback

-0.13

Mai

-0.13

urr

-0.13

ulumi

-0.13

POSITIVE LOGITS

uyla

0.16

 note

0.16

antor

0.15

icker

0.15

(note

0.15

ekim

0.15

cks

0.15

Pocket

0.15

asin

0.15

-note

0.14

Activations Density 0.067%

text that references or discusses records and official documentation

No Comments

No Known Activations