INDEX

Explanations

references to specific institutions, awards, or entities related to education and film

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

opsis

-0.18

olla

-0.15

loff

-0.14

apur

-0.14

OPSIS

-0.13

neau

-0.13

fff

-0.13

 ëĦ¤ìĿ´íĬ¸

-0.13

Ð»ÐºÐ¸

-0.13

eryl

-0.13

POSITIVE LOGITS

Lit

0.14

 Fare

0.13

linger

0.13

Fmt

0.13

æģ¯

0.13

atoire

0.12

essed

0.12

.business

0.12

angler

0.12

aims

0.12

Activations Density 0.096%

references to specific institutions, awards, or entities related to education and film

No Comments

No Known Activations