INDEX

Explanations

names or titles that are notably prominent in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

CIS

-0.15

 distance

-0.15

 Distance

-0.15

amt

-0.15

ione

-0.15

 Mate

-0.14

ostel

-0.14

ones

-0.14

icas

-0.14

 Ð¿Ð¾Ð³

-0.14

POSITIVE LOGITS

boro

0.14

 Edwards

0.14

aylight

0.14

 royalties

0.14

illy

0.14

trap

0.14

enschaft

0.14

 blush

0.13

ë¶Ģ

0.13

 muse

0.13

Activations Density 0.049%

names or titles that are notably prominent in the text

No Comments

No Known Activations