INDEX

Explanations

references to titles of works or quotes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ð°ÑĢÑĩ

-0.17

okino

-0.16

Zug

-0.16

zel

-0.15

ãĥ³ãĥĶ

-0.15

ervo

-0.15

sole

-0.15

§è¡Į

-0.15

arius

-0.15

IFF

-0.15

POSITIVE LOGITS

ipar

0.16

 Principle

0.15

 Pulse

0.15

è½

0.14

oyer

0.14

 Dudley

0.14

Ø¶Ùħ

0.14

 principle

0.14

sted

0.14

 Brewing

0.13

Activations Density 0.050%

references to titles of works or quotes

No Comments

No Known Activations