INDEX

Explanations

formatting symbols and characters commonly used in code or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 fear

-0.15

FG

-0.14

mad

-0.14

éļ

-0.14

 Matter

-0.13

 Ents

-0.13

ÙĪØ§Ø¡

-0.13

tel

-0.13

adin

-0.13

ulos

-0.13

POSITIVE LOGITS

ASTER

0.17

oyer

0.16

_axis

0.15

 abstract

0.15

abstract

0.14

->__

0.14

_Abstract

0.14

_abstract

0.14

 spice

0.14

Abstract

0.14

Activations Density 0.077%

formatting symbols and characters commonly used in code or programming contexts

No Comments

No Known Activations