INDEX

Explanations

technical language and concepts related to programming and code structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 simpl

-0.17

_nth

-0.15

 realism

-0.14

ory

-0.14

Liv

-0.14

ouser

-0.14

chwitz

-0.14

 Ø³Ø§Ùħ

-0.14

orio

-0.14

isha

-0.13

POSITIVE LOGITS

 bullet

0.24

 maintain

0.24

idi

0.23

ext

0.23

 clean

0.22

 lean

0.21

 portable

0.21

rob

0.20

 Maintain

0.20

 thread

0.20

Activations Density 0.130%

technical language and concepts related to programming and code structure

No Comments

No Known Activations