INDEX

Explanations

concepts related to software architecture and design principles

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

à¤¯à¤¨

-0.14

xad

-0.14

nist

-0.13

_modifier

-0.13

eken

-0.13

ORY

-0.13

plen

-0.13

æ¯ķ

-0.13

Void

-0.13

olls

-0.13

POSITIVE LOGITS

Reusable

0.17

 reusable

0.15

erne

0.15

Reuse

0.15

rani

0.15

hips

0.14

oes

0.14

opard

0.14

æĬ½

0.14

.bunifuFlatButton

0.14

Activations Density 0.148%

concepts related to software architecture and design principles

No Comments

No Known Activations