INDEX

Explanations

structured paths or URLs in technical text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

bedo

-0.17

inus

-0.16

vit

-0.15

ippi

-0.15

legate

-0.14

 habit

-0.14

urrent

-0.14

 vÃŃ

-0.14

ledo

-0.14

omain

-0.14

POSITIVE LOGITS

ngo

0.16

 serialVersionUID

0.15

 abstract

0.14

chk

0.14

 heterosexual

0.14

nee

0.14

opathy

0.13

ISC

0.13

boxed

0.13

Activations Density 0.020%

structured paths or URLs in technical text

No Comments

No Known Activations

structured paths or URLs in technical text

No Comments

No Known Activations