INDEX

Explanations

instructions related to completing forms or applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

orthand

-0.18

asca

-0.15

TPM

-0.15

ille

-0.15

wis

-0.14

HIR

-0.14

boru

-0.14

_ISO

-0.14

GenerationStrategy

-0.14

 pari

-0.14

POSITIVE LOGITS

aro

0.17

aines

0.16

 doldur

0.16

angan

0.15

IBUTES

0.15

ighton

0.15

omez

0.14

ëł¬

0.14

 Natasha

0.14

compact

0.14

Activations Density 0.020%

instructions related to completing forms or applications

No Comments

No Known Activations