INDEX

Explanations

programming annotations and metadata in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Nagar

-0.18

ouns

-0.16

 villagers

-0.15

antee

-0.14

angelo

-0.14

enko

-0.14

Ã«n

-0.13

::$_

-0.13

rn

-0.13

ang

-0.13

POSITIVE LOGITS

abbo

0.19

azu

0.15

umper

0.15

Hod

0.14

abd

0.14

orest

0.13

 SavaÅŁ

0.13

pesan

0.13

ignon

0.13

Activations Density 0.010%

programming annotations and metadata in code

No Comments

No Known Activations