INDEX

Explanations

references to books and literature

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

ebra

-0.15

ocale

-0.14

æ¨ĵ

-0.14

oust

-0.14

reib

-0.14

ãĥĥãĥĹ

-0.14

osto

-0.13

 Attachment

-0.13

abase

-0.13

POSITIVE LOGITS

ANE

0.16

.sd

0.15

 Termin

0.15

ÑĥÐ²

0.14

.ua

0.14

ernel

0.14

ivery

0.14

engo

0.14

istik

0.14

wc

0.14

Activations Density 0.016%

references to books and literature

No Comments

No Known Activations