INDEX

Explanations

terms and concepts related to gaming mechanics, specifically for character classes and their abilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

phony

-0.16

moid

-0.15

Ð¾Ð»Ñı

-0.15

kud

-0.15

mons

-0.15

orz

-0.15

LIKELY

-0.15

ÏħÏĦÏĮ

-0.15

yte

-0.14

Äı

-0.14

POSITIVE LOGITS

agon

0.16

frontend

0.14

osl

0.14

apor

0.14

ask

0.14

 bombard

0.14

AGON

0.14

 variable

0.14

amil

0.14

Activations Density 0.044%

terms and concepts related to gaming mechanics, specifically for character classes and their abilities

No Comments

No Known Activations