INDEX

Explanations

proper nouns 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

alm

-0.17

ucch

-0.16

nid

-0.15

Ð°Ð½Ð¸ÑĨ

-0.15

ocale

-0.15

obb

-0.14

aÃ±

-0.14

entries

-0.14

ghi

-0.14

ÙĪØ§Ø¡

-0.14

POSITIVE LOGITS

 sext

0.15

WIN

0.15

inson

0.14

.way

0.13

ils

0.13

 Cath

0.13

æ¸Ī

0.13

bab

0.13

Activations Density 0.030%

proper nouns and titles

No Comments

No Known Activations

proper nouns and titles

No Comments

No Known Activations