INDEX

Explanations

references to individual people and their life events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 sebagai

-0.15

rÃ¡f

-0.14

 Arlington

-0.13

¦æĥħ

-0.12

aired

-0.12

agu

-0.12

arÄ±m

-0.12

.visitMethod

-0.12

 addAction

-0.11

.EntityFramework

-0.11

POSITIVE LOGITS

As

1.01

AS

0.94

As

0.90

AS

0.82

_as

0.82

.as

0.80

_AS

0.76

_As

0.75

-as

0.74

.As

0.72

Activations Density 0.836%

references to individual people and their life events

No Comments

No Known Activations