INDEX

Explanations

phrases indicating methods or ways of doing something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ANGE

-0.16

infra

-0.14

STR

-0.14

uD

-0.14

immel

-0.13

aliz

-0.13

iform

-0.13

opes

-0.13

eldom

-0.13

%"

-0.13

POSITIVE LOGITS

mada

0.17

Achie

0.15

scribe

0.15

achie

0.14

 achieve

0.14

 getting

0.14

unan

0.14

 Achie

0.14

get

0.14

ongoose

0.14

Activations Density 0.114%

phrases indicating methods or ways of doing something

No Comments

No Known Activations