INDEX

Explanations

references to locations and their significance in a contextual narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

nelly

-0.15

ambi

-0.15

 Pakistani

-0.15

Abr

-0.15

 Montana

-0.14

terra

-0.14

abase

-0.14

apy

-0.14

eya

-0.14

rael

-0.13

POSITIVE LOGITS

 Kent

0.44

 Canterbury

0.40

 Dover

0.37

Kent

0.37

 kent

0.34

 Maid

0.34

Tun

0.31

 Than

0.31

 Rochester

0.31

Ton

0.29

Activations Density 0.017%

references to locations and their significance in a contextual narrative

No Comments

No Known Activations