INDEX

Explanations

programming or code-related keywords 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 @ 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

ollen

-0.16

ucha

-0.15

ragen

-0.15

acci

-0.15

ÃŃf

-0.15

odal

-0.15

aida

-0.15

 Dann

-0.14

nad

-0.14

ÄĻd

-0.14

POSITIVE LOGITS

ONO

0.20

ouns

0.15

å§«

0.14

à¸±à¸ģà¸£

0.14

OFFSET

0.14

DeltaTime

0.13

_deinit

0.13

 glyc

0.13

_operand

0.13

 gent

0.13

Activations Density 0.133%

programming or code-related keywords and structures

No Comments

No Known Activations