INDEX

Explanations

numbers and statistics relevant to various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

rah

-0.20

ardash

-0.16

aÅ¼

-0.16

stor

-0.15

agne

-0.15

ourg

-0.15

gabe

-0.14

taj

-0.14

à¤Ĺà¤²

-0.14

ÃĹ↵↵

-0.14

POSITIVE LOGITS

.extension

0.15

eree

0.14

ery

0.14

esy

0.14

exels

0.14

stock

0.14

zee

0.14

Activations Density 0.115%

numbers and statistics relevant to various contexts

No Comments

No Known Activations