INDEX

Explanations

technical terms and code structure related to programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ois

-0.16

ropol

-0.15

strict

-0.14

aurant

-0.14

za

-0.14

otal

-0.14

bane

-0.14

quine

-0.13

ÐºÐ°Ñģ

-0.13

POSITIVE LOGITS

anske

0.15

å¯¶

0.15

 Hills

0.15

iode

0.14

ÙĩØ±

0.14

à¤¿à¤

0.14

.hy

0.14

 watering

0.14

 Boots

0.14

Nut

0.14

Activations Density 0.037%

technical terms and code structure related to programming

No Comments

No Known Activations