INDEX

Explanations

references to various object types within code, particularly in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ovation

-0.15

chner

-0.15

ow

-0.15

esk

-0.15

adin

-0.14

avin

-0.14

ows

-0.14

thed

-0.13

ome

-0.13

fall

-0.13

POSITIVE LOGITS

è´¨

0.17

è³ª

0.15

spath

0.15

ï¼ħ

0.15

onas

0.15

Ð¸ÐºÐ¸

0.14

iffies

0.14

liÅ¡

0.14

ÃľR

0.14

å¶

0.14

Activations Density 0.038%

references to various object types within code, particularly in programming contexts

No Comments

No Known Activations