INDEX

Explanations

references to events, awards, and recognition within various organizations or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

lap

-0.15

efd

-0.14

fft

-0.14

ç»ĵ

-0.14

eca

-0.13

 à¤ķà¤°à¤ķ

-0.13

ä¸ŃåŃ¦

-0.13

ä»ĺ

-0.13

bil

-0.13

POSITIVE LOGITS

oload

0.17

less

0.16

ilha

0.16

mtree

0.15

anonymous

0.15

kus

0.14

IGHL

0.14

iless

0.14

ulumi

0.14

 sund

0.14

Activations Density 0.360%

references to events, awards, and recognition within various organizations or contexts

No Comments

No Known Activations