INDEX

Explanations

occurrences 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

wick

-0.15

adora

-0.14

unny

-0.14

LR

-0.14

ĺìĿ´

-0.14

LBL

-0.14

isy

-0.14

 Laur

-0.14

 Tier

-0.13

lr

-0.13

POSITIVE LOGITS

 Niagara

0.16

alsa

0.14

 Mein

0.14

ÐºÑĥÑĤ

0.14

aber

0.14

iqueta

0.13

(ml

0.13

ÐµÑĢÐ°Ð¿

0.13

aret

0.13

cant

0.13

Activations Density 0.046%

occurrences of dates and temporal references

No Comments

No Known Activations