INDEX

Explanations

function definitions in code, particularly in Python

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Ð°Ð½Ð¾Ð²

-0.15

ondo

-0.14

æĸ·

-0.14

.ai

-0.13

 æĸ

-0.13

 Advance

-0.13

aticon

-0.13

ovich

-0.13

(Android

-0.13

çķ

-0.13

POSITIVE LOGITS

kou

0.15

dae

0.15

adas

0.14

ilogue

0.14

Ø¶ÙĪ

0.14

linger

0.14

uges

0.14

 analogy

0.14

URN

0.14

 Mayer

0.14

Activations Density 0.013%

function definitions in code, particularly in Python

No Comments

No Known Activations