INDEX

Explanations

specific numeric or coded values in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

à¤¹à¤²

-0.17

Ð¹Ð½

-0.17

antro

-0.16

lÃ¤

-0.16

arsers

-0.15

olio

-0.14

eliac

-0.14

ysters

-0.14

esModule

-0.14

ÑįÑĦ

-0.14

POSITIVE LOGITS

 third

0.24

rd

0.22

 Third

0.19

 THIRD

0.19

 Neutral

0.18

Third

0.17

third

0.17

-third

0.17

_third

0.17

Activations Density 0.964%

specific numeric or coded values in a structured format

No Comments

No Known Activations