INDEX

Explanations

names of people and their associated attributes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

egas

-0.17

icket

-0.17

Ð¾ÑĤÑĥ

-0.15

à¤¿à¤¯à¤¤

-0.15

det

-0.15

igt

-0.14

/browse

-0.14

_inverse

-0.14

gtk

-0.14

esco

-0.14

POSITIVE LOGITS

oseconds

0.14

uben

0.14

 Äĳá»Ŀi

0.14

.firebaseapp

0.14

InstantiationException

0.14

osy

0.14

0.13

avier

0.13

FTA

0.13

Activations Density 0.057%

names of people and their associated attributes

No Comments

No Known Activations