INDEX

Explanations

geographical names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

erti

-0.14

imson

-0.14

ields

-0.14

atori

-0.13

 Realty

-0.13

 Vine

-0.13

orde

-0.13

ydk

-0.13

ÏģÎ¸

-0.13

aniem

-0.13

POSITIVE LOGITS

-based

0.32

based

0.24

 native

0.24

_based

0.21

-Based

0.21

 resident

0.20

-native

0.20

 based

0.20

-born

0.19

 natives

0.18

Activations Density 0.094%

geographical names and locations

No Comments

No Known Activations