INDEX

Explanations

ordinal numbers and descriptors related to rankings or sizes

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

enko

-0.15

 Toro

-0.15

jan

-0.14

é³

-0.14

JNI

-0.14

æĸ

-0.14

gesi

-0.14

 DÆ°Æ¡ng

-0.14

tro

-0.13

POSITIVE LOGITS

irty

0.16

Cah

0.16

-largest

0.16

overall

0.15

arily

0.15

ledon

0.15

 overall

0.15

ponce

0.14

ÑģÐ¾Ðº

0.14

 Sick

0.14

Activations Density 0.030%

ordinal numbers and descriptors related to rankings or sizes

No Comments

No Known Activations