INDEX

Explanations

terms related to capability or capacity

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

_pb

-0.18

kaar

-0.18

ignet

-0.17

ropa

-0.16

antom

-0.16

athe

-0.16

ETO

-0.16

ethe

-0.15

ahan

-0.15

eka

-0.15

POSITIVE LOGITS

idades

0.17

ideographic

0.16

ities

0.16

antages

0.15

 ability

0.15

antage

0.14

åĲ§

0.14

iesen

0.14

 station

0.14

 subdiv

0.14

Activations Density 0.132%

terms related to capability or capacity

No Comments

No Known Activations