INDEX

Explanations

URLs or web-related content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-indent

-0.15

omba

-0.15

ç²Ĵ

-0.15

egas

-0.14

ator

-0.14

 typed

-0.14

ink

-0.14

*,

-0.14

erox

-0.14

POSITIVE LOGITS

ãĥ¼ãĥľ

0.18

.GPIO

0.16

-Fi

0.15

eel

0.15

orial

0.15

áº¿n

0.15

-Smith

0.14

aset

0.14

contri

0.14

emetery

0.14

Activations Density 0.016%

URLs or web-related content

No Comments

No Known Activations