INDEX

Explanations

occurrences of significant events or announcements in a specific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

oggles

-0.17

Ã´

-0.15

agram

-0.15

saf

-0.15

spl

-0.15

/constants

-0.14

oro

-0.14

UNG

-0.14

áº¡t

-0.14

 ÑĢÐ°ÑģÑĤ

-0.14

POSITIVE LOGITS

uitka

0.15

alars

0.15

rames

0.15

frauen

0.15

ÑĢÑĥÑĤ

0.14

.Xaml

0.14

pyx

0.14

-Semit

0.14

abis

0.14

rott

0.14

Activations Density 0.271%

occurrences of significant events or announcements in a specific context

No Comments

No Known Activations