INDEX

Explanations

mentions of novels and literary works

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

ansson

-0.17

alic

-0.17

abox

-0.16

yor

-0.16

wards

-0.16

mons

-0.15

yonel

-0.15

fre

-0.15

ed

-0.15

ASHBOARD

-0.15

POSITIVE LOGITS

ystack

0.16

mente

0.15

ijn

0.15

 Fiesta

0.14

cko

0.14

omain

0.13

lette

0.13

egt

0.13

 elig

0.13

-length

0.13

Activations Density 0.017%

mentions of novels and literary works

No Comments

No Known Activations