INDEX

Explanations

sequences of dates and temporal references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

pus

-0.16

emet

-0.16

orum

-0.15

fel

-0.14

hel

-0.14

è¡Ĺéģĵ

-0.14

erg

-0.14

ahi

-0.13

ynet

-0.13

fel

-0.13

POSITIVE LOGITS

 until

0.37

 till

0.30

 hasta

0.28

 onwards

0.28

 Until

0.27

until

0.26

 jusqu

0.26

Until

0.25

 atÃ©

0.24

 perspective

0.23

Activations Density 0.047%

sequences of dates and temporal references

No Comments

No Known Activations