INDEX

Explanations

various forms of categorization and classification within academic or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

_tD

-0.17

ÙĤØ¯

-0.16

ancode

-0.15

_tF

-0.15

%X

-0.14

ãĤ¤ãĤº

-0.14

ÙĪØŃ

-0.14

Ð¸ÑĢÐ°

-0.14

imeType

-0.14

apon

-0.14

POSITIVE LOGITS

NAS

0.16

Nib

0.15

UNT

0.15

 super

0.14

 habit

0.14

UDO

0.14

 reap

0.14

 Habit

0.13

 Lindsey

0.13

æ¯

0.13

Activations Density 0.019%

various forms of categorization and classification within academic or technical contexts

No Comments

No Known Activations