INDEX

Explanations

terms related to criticisms of art, particularly in film and literature, focusing on predictability and clichés

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

som

-0.17

assis

-0.16

 tender

-0.15

 Junk

-0.15

bill

-0.15

Ø¨Ø±ÛĮ

-0.15

stro

-0.15

ance

-0.14

ncia

-0.14

lian

-0.14

POSITIVE LOGITS

Ð»Ñĥ

0.15

ichert

0.14

otope

0.14

lus

0.14

immel

0.14

ìĨĶ

0.13

 Ð¿Ð¾Ð±Ð°

0.13

.extent

0.13

chant

0.13

HING

0.13

Activations Density 0.164%

terms related to criticisms of art, particularly in film and literature, focusing on predictability and clichés

No Comments

No Known Activations