INDEX

Explanations

occurrences of HTML elements or document structure indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

adier

-0.17

enko

-0.15

 trend

-0.15

nummer

-0.14

aber

-0.14

elia

-0.14

mares

-0.14

esda

-0.13

aterno

-0.13

 Champagne

-0.13

POSITIVE LOGITS

DOCTYPE

0.32

doctype

0.27

ENTITY

0.19

DOC

0.18

âĢĲâĢĲ

0.18

ELEMENT

0.17

DO

0.17

ÑĥÑĢÑĥ

0.17

IDO

0.15

anova

0.15

Activations Density 0.009%

occurrences of HTML elements or document structure indicators

No Comments

No Known Activations