INDEX

Explanations

technical terminology related to programming and software development environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

dyby

-0.17

nete

-0.16

gren

-0.14

ichel

-0.14

.sales

-0.14

æĮ¯

-0.14

à¸ģà¸£à¸£à¸¡

-0.14

 Decomp

-0.14

andr

-0.14

 Î±Î½Î¬

-0.14

POSITIVE LOGITS

 exact

0.16

ucker

0.16

osas

0.14

ought

0.14

exact

0.14

 Exact

0.14

 build

0.14

 running

0.13

)\<

0.13

Activations Density 0.060%

technical terminology related to programming and software development environments

No Comments

No Known Activations