INDEX

Explanations

references to specific organizations or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ilde

-0.16

_bs

-0.14

alth

-0.14

apesh

-0.14

eming

-0.14

 Patton

-0.14

iry

-0.14

 nurs

-0.14

.bs

-0.13

Lt

-0.13

POSITIVE LOGITS

 helm

0.19

 company

0.18

 institution

0.17

 Firm

0.16

HQ

0.15

 Company

0.15

innacle

0.15

æ°Ĺ

0.15

 organisation

0.15

 companies

0.15

Activations Density 0.068%

references to specific organizations or institutions

No Comments

No Known Activations