INDEX

Explanations

references to specific locations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

berry

-0.15

 multin

-0.15

 compass

-0.15

aru

-0.14

 Ãºzem

-0.14

fram

-0.14

Lol

-0.14

hrad

-0.14

atures

-0.14

alem

-0.14

POSITIVE LOGITS

aison

0.15

-LAST

0.15

 sona

0.15

jÃŃt

0.15

TAX

0.15

_RT

0.14

à¹īà¸Ī

0.14

QRST

0.14

leep

0.14

criptors

0.14

Activations Density 0.024%

references to specific locations or entities

No Comments

No Known Activations

references to specific locations or entities

No Comments

No Known Activations