INDEX

Explanations

technical identifiers and specific family-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Ð²ÐºÐ»ÑİÑĩ

-0.16

 INCLUDING

-0.15

 comprising

-0.14

Including

-0.14

INCLUDING

-0.14

 Corporation

-0.14

 Including

-0.14

 INCLUDED

-0.14

åĮħæĭ¬

-0.14

 inclu

-0.14

POSITIVE LOGITS

and

0.18

 specialised

0.16

iggins

0.15

adients

0.14

 graduating

0.13

abant

0.13

 specialist

0.13

 trained

0.13

 marrying

0.13

 immigr

0.13

Activations Density 0.035%

technical identifiers and specific family-related terminology

No Comments

No Known Activations