INDEX

Explanations

references to academic research and academic terms related to studies

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

-0.16

Ð¸ÑĪ

-0.15

onne

-0.15

-0.14

ONTAL

-0.14

yle

-0.14

.strategy

-0.14

Ð±ÑĥÐ´ÑĮ

-0.14

STITUTE

-0.14

oid

-0.14

POSITIVE LOGITS

hall

0.17

avax

0.17

ETF

0.15

ret

0.15

.Ret

0.15

lap

0.14

rite

0.14

deme

0.14

cala

0.14

 Lana

0.14

Activations Density 0.025%

references to academic research and academic terms related to studies

No Comments

No Known Activations