INDEX

Explanations

references to artists, their works, and historical figures in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

vier

-0.16

Named

-0.14

å°¾

-0.13

ÑĳÐ¼

-0.13

xaa

-0.13

ÏĢÎ¿ÏĦÎµ

-0.13

ê³

-0.13

 helm

-0.13

fal

-0.13

Parking

-0.12

POSITIVE LOGITS

0.23

 born

0.23

0.21

0.20

0.19

 died

0.18

 Born

0.18

Activations Density 0.116%

references to artists, their works, and historical figures in various contexts

No Comments

No Known Activations