INDEX

Explanations

occurrences of weekly events or schedules

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

-0.17

fty

-0.15

-0.14

èªĮ

-0.14

issing

-0.14

ÙĪÛĮÙĩ

-0.13

ptom

-0.13

Ð¾Ñī

-0.13

į¼

-0.13

POSITIVE LOGITS

0.39

Û²Û°Û±

0.24

ados

0.18

gas

0.17

uras

0.16

0.15

ots

0.15

¨

0.15

aturas

0.15

inas

0.15

Activations Density 0.044%

occurrences of weekly events or schedules

No Comments

No Known Activations