INDEX

Explanations

temporal or duration-related references regarding events or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ilog

-0.17

 Shift

-0.16

lech

-0.16

-0.15

mor

-0.15

umm

-0.14

iw

-0.14

eni

-0.14

ota

-0.14

lem

-0.14

POSITIVE LOGITS

(duration

0.17

until

0.16

-duration

0.16

anship

0.16

 duration

0.15

 Duration

0.15

abyrin

0.15

iode

0.15

airo

0.14

beit

0.14

Activations Density 0.292%

temporal or duration-related references regarding events or services

No Comments

No Known Activations