INDEX

Explanations

patterns in code related to method calls and parameter checking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ollo

-0.16

orners

-0.16

Ãªu

-0.15

amos

-0.15

ker

-0.15

æĸ¹

-0.14

arpa

-0.14

ãĥ¼ãĥł

-0.14

late

-0.14

 dist

-0.13

POSITIVE LOGITS

 onTouch

0.16

 McGregor

0.16

iner

0.15

inct

0.15

_detach

0.15

velt

0.15

 Moran

0.15

cken

0.14

 Holt

0.14

ëĬ¥

0.14

Activations Density 0.016%

patterns in code related to method calls and parameter checking

No Comments

No Known Activations