INDEX

Explanations

specific numeric values or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 McMahon

-0.17

iges

-0.14

 seiz

-0.14

 Bender

-0.14

eren

-0.14

zek

-0.14

ayn

-0.14

 Burke

-0.14

SES

-0.14

POSITIVE LOGITS

0.28

0.25

0.24

0.23

0.22

Activations Density 0.020%

specific numeric values or identifiers

No Comments

No Known Activations