INDEX

Explanations

programming-related terms and phrases indicating limitations, responsibilities, or specific attributes associated with legal or contractual agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Uncomment

-0.17

alion

-0.15

ht

-0.15

istar

-0.14

ifold

-0.14

ippo

-0.14

 Legion

-0.14

ysters

-0.14

ihar

-0.13

ception

-0.13

POSITIVE LOGITS

ody

0.16

/Gate

0.16

oni

0.15

SSF

0.15

jal

0.14

uur

0.14

StrictEqual

0.14

ewire

0.14

oma

0.14

ilst

0.13

Activations Density 0.001%

programming-related terms and phrases indicating limitations, responsibilities, or specific attributes associated with legal or contractual agreements

No Comments

No Known Activations