INDEX

Explanations

numerical references and ordinal indicators related to events or sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

.mit

-0.16

 Boeh

-0.16

ajor

-0.15

amps

-0.15

ÑĨÐ¸ÑĤ

-0.14

èĹı

-0.14

 RectTransform

-0.14

ourg

-0.14

ird

-0.14

urr

-0.14

POSITIVE LOGITS

ore

0.21

ett

0.18

anni

0.17

 chili

0.17

enn

0.16

mes

0.16

gg

0.16

 anni

0.16

enne

0.16

 volte

0.16

Activations Density 0.006%

numerical references and ordinal indicators related to events or sequences

No Comments

No Known Activations