INDEX

Explanations

phrases indicating a need for improvement or growth

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ava

-0.15

à¸«

-0.14

 familiar

-0.14

 fist

-0.14

mn

-0.14

odore

-0.14

 attempt

-0.14

Fro

-0.14

dir

-0.13

POSITIVE LOGITS

ï»¿#

0.18

iola

0.16

berger

0.15

UsageId

0.15

SEQUENTIAL

0.15

iyel

0.15

rieve

0.15

ÐĴÐ¡

0.15

ocos

0.15

OptionsResolver

0.14

Activations Density 0.162%

phrases indicating a need for improvement or growth

No Comments

No Known Activations