INDEX

Explanations

discussions 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 @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

inja

-0.17

LOW

-0.15

.cx

-0.15

.FONT

-0.14

Sah

-0.14

Lug

-0.14

 bash

-0.14

Î²Î¬

-0.13

uation

-0.13

ls

-0.13

POSITIVE LOGITS

enance

0.17

aned

0.16

0.15

aktion

0.15

conto

0.15

åĮ

0.14

ICI

0.14

amespace

0.14

 Locke

0.14

ackage

0.14

Activations Density 0.347%

discussions related to programming and code structure

No Comments

No Known Activations