INDEX

Explanations

terms related to processing and filtering options in a data structure or programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

OptionsResolver

-0.17

/IP

-0.15

OffsetTable

-0.15

GenerationStrategy

-0.15

/Gate

-0.14

uples

-0.14

unar

-0.14

elez

-0.14

_fsm

-0.14

Ëĺ

-0.14

POSITIVE LOGITS

 Rena

0.15

/original

0.15

wor

0.15

ies

0.14

ly

0.14

ail

0.14

ashi

0.14

osg

0.14

axy

0.14

ness

0.14

Activations Density 0.228%

terms related to processing and filtering options in a data structure or programming context

No Comments

No Known Activations