INDEX

Explanations

references to locations or places

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

tering

-0.16

IV

-0.15

.tpl

-0.14

arella

-0.14

éĩ

-0.14

iv

-0.14

Ã¶z

-0.14

teri

-0.14

datable

-0.14

efe

-0.14

POSITIVE LOGITS

eÃ§

0.16

ãĥ¶

0.16

bins

0.16

upos

0.15

vana

0.15

æ³Ĭ

0.14

KL

0.14

getSingleton

0.14

 Epoch

0.14

PEG

0.14

Activations Density 0.101%

references to locations or places

No Comments

No Known Activations