INDEX

Explanations

references to "internal" aspects of processes, systems, and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

.metro

-0.15

APTER

-0.15

WithEmail

-0.14

ÑĤÐµ

-0.14

asename

-0.14

ÎºÎ¹

-0.14

loquent

-0.14

anna

-0.14

Ð½Ð¾Ñģ

-0.14

emia

-0.13

POSITIVE LOGITS

most

0.27

/Internal

0.21

/internal

0.21

halb

0.20

/back

0.17

/out

0.17

-facing

0.17

 workings

0.16

ized

0.16

thew

0.16

Activations Density 0.037%

references to "internal" aspects of processes, systems, and structures

No Comments

No Known Activations