INDEX

Explanations

the name "Philip."

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

strup

-0.15

akeup

-0.14

pectral

-0.14

ÐµÐ»Ñı

-0.14

rak

-0.14

uration

-0.14

.CompilerServices

-0.14

POSITIVE LOGITS

ModelProperty

0.15

fully

0.15

adelphia

0.14

_adc

0.14

ãĥ£

0.14

son

0.14

erea

0.14

-scrollbar

0.14

ips

0.14

orde

0.14

Activations Density 0.003%

the name "Philip."

No Comments

No Known Activations