INDEX

Explanations

dates and numerical information, particularly related to years and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

yr

-0.18

Profiles

-0.15

ongyang

-0.14

dv

-0.14

ext

-0.14

heed

-0.13

æĺ¥

-0.13

esta

-0.13

argar

-0.13

ort

-0.13

POSITIVE LOGITS

ä»½

0.22

 monthly

0.20

 month

0.20

 Month

0.19

 Monthly

0.18

(month

0.18

/month

0.17

.Month

0.17

 months

0.15

yte

0.15

Activations Density 0.084%

dates and numerical information, particularly related to years and events

No Comments

No Known Activations