INDEX

Explanations

references to digital media or specific digital platforms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Ð¾Ð²Ð¸Ñĩ

-0.15

ocket

-0.15

ampa

-0.14

inia

-0.14

íĶ¼

-0.13

Ð¾ÑģÑĤÑĥÐ¿

-0.13

 Synd

-0.13

uur

-0.13

akh

-0.13

atile

-0.13

POSITIVE LOGITS

oyo

0.15

ajo

0.15

friend

0.15

ãģ£ãģ¡

0.14

\grid

0.14

Ã¤ter

0.14

uele

0.13

ÑĢÑĥÐ¿Ð¿

0.13

isor

0.13

Fer

0.13

Activations Density 0.011%

references to digital media or specific digital platforms

No Comments

No Known Activations