INDEX

Explanations

references to notable individuals or authors

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 recru

-0.15

âĢİ

-0.15

 Pell

-0.14

ICODE

-0.14

/interface

-0.14

 afterEach

-0.14

onu

-0.13

å¼ĺ

-0.13

rum

-0.13

Ð¾Ð±Ð°

-0.13

POSITIVE LOGITS

ibold

0.22

á»Ŀ

0.16

acle

0.16

stor

0.15

DET

0.14

AllowAnonymous

0.14

ä»¶

0.13

ohan

0.13

.framework

0.13

innen

0.13

Activations Density 0.010%

references to notable individuals or authors

No Comments

No Known Activations