INDEX

Explanations

references to licenses and copyright information

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Bast

-0.18

-0.17

 Ston

-0.16

ÐŁÐļ

-0.15

til

-0.15

 fist

-0.15

ady

-0.14

uch

-0.14

ullet

-0.14

ve

-0.14

POSITIVE LOGITS

);$

0.17

ëŀ

0.16

 licenses

0.15

 LICENSE

0.15

ÑĩÑĥ

0.15

ene

0.15

 IHttp

0.15

æķı

0.15

 Licensed

0.14

});č↵

0.14

Activations Density 0.002%

references to licenses and copyright information

No Known Activations