INDEX

Explanations

references to computer science or related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

anta

-0.17

 Kear

-0.16

aku

-0.15

eturn

-0.14

ire

-0.14

ache

-0.14

atis

-0.14

etas

-0.14

ached

-0.14

POSITIVE LOGITS

MLE

0.15

ÌĨ

0.15

appa

0.15

 ìļĶ

0.14

esa

0.14

-action

0.14

-effect

0.14

à¸²à¸Īà¸²à¸ģ

0.14

rz

0.13

DSA

0.13

Activations Density 0.008%

references to computer science or related topics

No Comments

No Known Activations