INDEX

Explanations

references to exceptions and conditions regarding rules or regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

asher

-0.15

urar

-0.14

avel

-0.14

áº¡c

-0.13

 obligatory

-0.13

BackgroundColor

-0.13

redi

-0.13

 dump

-0.13

ash

-0.13

lico

-0.13

POSITIVE LOGITS

 exceptions

0.90

 exception

0.85

 Exceptions

0.73

exceptions

0.70

 EXCEPTION

0.65

exception

0.64

 Exception

0.64

Exceptions

0.63

Exception

0.58

 exemptions

0.58

Activations Density 0.252%

references to exceptions and conditions regarding rules or regulations

No Comments

No Known Activations