INDEX

Explanations

comparative terms and relationships regarding size and quantity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jni

-0.15

ancode

-0.14

anche

-0.14

alara

-0.14

 exhaust

-0.14

Ð°ÑĢÐ°ÑĤ

-0.14

positor

-0.14

 buried

-0.14

é¨

-0.14

 CHANGE

-0.14

POSITIVE LOGITS

toa

0.16

æŀľ

0.15

emy

0.15

esson

0.15

0.14

emann

0.14

awah

0.14

Lum

0.14

Activations Density 0.031%

comparative terms and relationships regarding size and quantity

No Comments

No Known Activations