INDEX

Explanations

phrases indicating complexity or nuances in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

SystemService

-0.15

.addAll

-0.15

.nextSibling

-0.15

.badlogic

-0.14

ceph

-0.14

.IsMatch

-0.14

Pry

-0.13

Ð¶Ð´

-0.13

æĹıèĩªæ²»

-0.13

POSITIVE LOGITS

errat

0.16

licer

0.15

illes

0.15

_bundle

0.14

ollo

0.14

 Oswald

0.14

Į

0.14

olina

0.14

anca

0.14

ktor

0.14

Activations Density 0.275%

phrases indicating complexity or nuances in discussions

No Comments

No Known Activations