INDEX

Explanations

programming-related syntax or structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Glasgow

-0.20

elfast

-0.19

 Belfast

-0.18

 Scots

-0.18

 Carnegie

-0.17

 Ireland

-0.17

 Dublin

-0.17

orra

-0.17

 Highland

-0.17

 Irish

-0.16

POSITIVE LOGITS

 Suffolk

0.17

.boolean

0.15

RuleContext

0.15

 Crowley

0.15

ampo

0.15

éĤ¦

0.14

ISODE

0.14

 Hook

0.14

Pur

0.14

 Massachusetts

0.14

Activations Density 0.002%

programming-related syntax or structure

No Comments

No Known Activations