INDEX

Explanations

references to portraits and portraiture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ermal

-0.17

eny

-0.16

erman

-0.15

 DÃ¼n

-0.14

 Beste

-0.14

olland

-0.14

ging

-0.14

_VIS

-0.14

 forefront

-0.14

arl

-0.14

POSITIVE LOGITS

teri

0.17

 dela

0.15

Tok

0.15

.ds

0.15

 Mellon

0.14

"('

0.14

 Meadows

0.14

agens

0.14

rypt

0.14

tgt

0.14

Activations Density 0.014%

references to portraits and portraiture

No Comments

No Known Activations