INDEX

Explanations

key details and mentions of specific events or releases related to movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

eba

-0.16

 Scalars

-0.15

rej

-0.14

apos

-0.14

Fen

-0.14

umer

-0.14

azed

-0.14

amos

-0.13

quito

-0.13

Understanding

-0.13

POSITIVE LOGITS

entar

0.17

iddet

0.15

IDD

0.15

emez

0.14

(=)

0.14

resar

0.14

hev

0.14

istrovstvÃŃ

0.14

dech

0.14

iani

0.13

Activations Density 0.276%

key details and mentions of specific events or releases related to movies

No Comments

No Known Activations