INDEX

Explanations

occurrences of the word "rob" and its variants, indicating themes of theft or robbery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

bert

-0.20

-0.18

park

-0.18

pom

-0.18

pv

-0.18

erton

-0.17

istic

-0.17

POSITIVE LOGITS

sy

0.22

tt

0.21

oster

0.19

ssa

0.18

sin

0.17

ta

0.17

ro

0.17

 Ð£ÐºÑĢÐ°ÑĹ

0.17

ving

0.16

 requestOptions

0.16

Activations Density 0.006%

occurrences of the word "rob" and its variants, indicating themes of theft or robbery

No Comments

No Known Activations