INDEX

Explanations

terms related to prestigious film awards

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

nist

-0.16

agnet

-0.15

adge

-0.15

laus

-0.14

Ð¾Ð»Ñİ

-0.14

onna

-0.14

arget

-0.14

ï¾ŀ

-0.14

_pins

-0.13

Å¡tÄĽ

-0.13

POSITIVE LOGITS

ilent

0.15

pa

0.14

borough

0.14

kup

0.14

avan

0.14

 Ø¹Ø´

0.13

deal

0.13

 pragma

0.13

.gov

0.13

igon

0.13

Activations Density 0.006%

terms related to prestigious film awards

No Comments

No Known Activations