INDEX

Explanations

terms related to programming and data manipulation in code

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

chs

-0.15

.IContainer

-0.14

iq

-0.14

hti

-0.14

ogo

-0.14

ANNEL

-0.14

-0.13

oro

-0.13

hart

-0.13

POSITIVE LOGITS

efon

0.17

 pointed

0.14

linky

0.14

ief

0.14

à¹Ĥà¸Ī

0.14

Å¡ak

0.14

ekim

0.14

Bib

0.14

ãĤ«ãĥ«

0.14

acey

0.13

Activations Density 0.256%

terms related to programming and data manipulation in code

No Comments

No Known Activations