INDEX

Explanations

terms related to assignments and legal agreements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

//{{

-0.16

iente

-0.14

olie

-0.14

adelphia

-0.14

andas

-0.14

INC

-0.14

tk

-0.14

Î¸Ïħ

-0.13

 Cruz

-0.13

nc

-0.13

POSITIVE LOGITS

itto

0.15

 Ownership

0.15

 Marketable

0.15

 ownership

0.15

ħĮ

0.14

Ownership

0.14

Swift

0.14

 Swift

0.14

 Holdings

0.13

PLICATE

0.13

Activations Density 0.002%

terms related to assignments and legal agreements

No Comments

No Known Activations