INDEX

Explanations

various types of information that are relevant for communication, documentation, or assessment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ã¹

-0.17

_REDIRECT

-0.15

PRINTF

-0.15

alan

-0.15

 initWithNibName

-0.14

à¸²à¸¢à¸Ļ

-0.14

 Identifier

-0.14

pen

-0.13

Dag

-0.13

ana

-0.13

POSITIVE LOGITS

/info

0.18

 information

0.18

-information

0.18

usz

0.17

 gathered

0.17

-valu

0.16

 useClass

0.15

information

0.15

Rh

0.15

odic

0.15

Activations Density 0.160%

various types of information that are relevant for communication, documentation, or assessment

No Comments

No Known Activations