INDEX

Explanations

names of brands and companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 tavs

-0.15

fÃ¼hr

-0.15

.microsoft

-0.15

agate

-0.14

ense

-0.14

/generated

-0.13

leader

-0.13

 Wikispecies

-0.13

odu

-0.13

.opendaylight

-0.13

POSITIVE LOGITS

 Productions

0.19

eki

0.16

 imprint

0.15

skirts

0.15

 productions

0.15

RVA

0.15

 Collective

0.14

 Ð¼Ð¸Ð½Ñĥ

0.14

works

0.14

Activations Density 0.375%

names of brands and companies

No Comments

No Known Activations