INDEX

Explanations

structured data references and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

lexical

-0.18

 libertarian

-0.17

éľ²

-0.16

 leak

-0.15

literal

-0.15

 leaks

-0.15

Î»Î¿Î¹

-0.14

 legis

-0.14

 libre

-0.14

.po

-0.14

POSITIVE LOGITS

(IL

0.32

SL

0.32

AL

0.31

TL

0.31

VL

0.31

PL

0.30

JL

0.30

LL

0.30

CL

0.30

DL

0.30

Activations Density 0.223%

structured data references and identifiers

No Comments

No Known Activations