INDEX

Explanations

specific names and details pertaining to individuals and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

kli

-0.19

iyan

-0.18

 kontakte

-0.18

jian

-0.16

çħ¤

-0.16

 facet

-0.15

zm

-0.15

 kÃ¥

-0.15

 enumerable

-0.14

jen

-0.14

POSITIVE LOGITS

og

0.16

asjon

0.16

emens

0.16

IMER

0.15

och

0.15

Ã¥l

0.15

raham

0.15

ÚĨØ§Ø±

0.15

strup

0.15

utow

0.14

Activations Density 0.350%

specific names and details pertaining to individuals and locations

No Comments

No Known Activations