INDEX

Explanations

iterations of the word "make" and related terms in the context of creating or producing items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ãĥ¼ãĥ«

-0.14

ifen

-0.14

icit

-0.14

ÑģÐ°Ð¼

-0.14

eltas

-0.14

LOCKS

-0.14

Ð½Ð¸ÑĨÑı

-0.14

idget

-0.14

vale

-0.14

PUTE

-0.14

POSITIVE LOGITS

ature

0.15

arger

0.14

utow

0.14

Ð¾Ð³ÑĢÐ°

0.14

 Daly

0.14

onda

0.14

BS

0.14

ocker

0.14

Tracker

0.14

imson

0.13

Activations Density 0.113%

iterations of the word "make" and related terms in the context of creating or producing items

No Comments

No Known Activations