INDEX

Explanations

instances of code or programming terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lever

-0.16

 å¥

-0.15

 Airways

-0.14

ocha

-0.14

opard

-0.14

fod

-0.14

umas

-0.14

ãĤ¢ãĥ¼

-0.14

 ÐºÐ¾Ñģ

-0.14

eway

-0.14

POSITIVE LOGITS

amam

0.15

ä½µ

0.15

ÐŁÐŀ

0.15

0.14

ieux

0.14

ilot

0.14

à¤¾:

0.14

POV

0.13

REEN

0.13

Activations Density 0.019%

instances of code or programming terminology

No Comments

No Known Activations