INDEX

Explanations

phrases and terms associated with legal or regulatory changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

iox

-0.15

/repository

-0.14

aupt

-0.14

ijd

-0.13

 continuation

-0.13

oken

-0.13

POSITIVE LOGITS

 effective

0.62

effective

0.54

 Effective

0.54

Effective

0.50

 EFFECT

0.49

-effective

0.47

_effect

0.45

 effectiveness

0.45

 effect

0.43

 efect

0.41

Activations Density 0.144%

phrases and terms associated with legal or regulatory changes

No Comments

No Known Activations