INDEX

Explanations

references to regular intervals of time, specifically focused on weekly and monthly occurrences

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

nm

-0.17

 recent

-0.15

es

-0.15

ur

-0.15

alk

-0.15

hu

-0.14

zi

-0.14

 Stanley

-0.14

urat

-0.14

Æ°á»Ľng

-0.14

POSITIVE LOGITS

/month

0.29

mente

0.22

ities

0.19

idades

0.19

 dose

0.18

haps

0.17

ë§Īëĭ¤

0.16

ized

0.16

idad

0.15

ity

0.15

Activations Density 0.027%

references to regular intervals of time, specifically focused on weekly and monthly occurrences

No Comments

No Known Activations