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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ÐµÐ¹Ð½

-0.15

zych

-0.15

ernen

-0.14

avn

-0.14

esel

-0.14

á»īnh

-0.14

ogl

-0.14

uddy

-0.13

 cush

-0.13

 Charge

-0.13

POSITIVE LOGITS

ergus

0.15

vo

0.15

ri

0.15

bab

0.14

Flip

0.14

 scand

0.14

 Ð²Ð¸ÑĤ

0.13

ropy

0.13

isers

0.13

Activations Density 0.005%

programming annotations and metadata in code

No Comments

No Known Activations