INDEX

Explanations

phrases emphasizing the significance or attributes of something

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

ided

-0.16

enth

-0.15

zell

-0.15

ÄįÃŃ

-0.14

 Eins

-0.14

foundland

-0.14

CLS

-0.14

uce

-0.14

 rekl

-0.14

etimes

-0.13

POSITIVE LOGITS

egin

0.18

nodes

0.15

uman

0.15

onth

0.14

monds

0.14

Lane

0.14

 Lionel

0.14

æµľ

0.13

arris

0.13

icol

0.13

Activations Density 0.081%

phrases emphasizing the significance or attributes of something

No Comments

No Known Activations