INDEX

Explanations

mentions of historical topics or events

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

Rel

-0.16

aku

-0.15

éľ

-0.15

_md

-0.15

 Beat

-0.14

 ÑĪÐ¸

-0.14

 FontStyle

-0.14

/Dk

-0.14

 Rockefeller

-0.13

 Orthodox

-0.13

POSITIVE LOGITS

 Celtic

0.25

 roman

0.22

 Gaul

0.20

 tribal

0.19

Britain

0.19

 Britain

0.19

 Romans

0.18

 Roman

0.18

 Tribal

0.18

 Celtics

0.18

Activations Density 0.075%

mentions of historical topics or events

No Comments

No Known Activations

mentions of historical topics or events

No Comments

No Known Activations