INDEX

Explanations

references to movies and TV shows, particularly their titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ÑĢÐµÐ¶

-0.17

isman

-0.17

.scalablytyped

-0.15

oblin

-0.15

hausen

-0.15

usa

-0.14

anja

-0.14

ibal

-0.14

YLON

-0.14

apolis

-0.14

POSITIVE LOGITS

udded

0.15

 Jerusalem

0.15

Bak

0.15

TECTED

0.15

Div

0.14

Ab

0.14

Mon

0.14

re

0.13

fat

0.13

Activations Density 0.110%

references to movies and TV shows, particularly their titles

No Comments

No Known Activations