INDEX

Explanations

geographic or historical references related to places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

EDA

-0.16

sher

-0.15

atas

-0.14

inkel

-0.14

 sclerosis

-0.14

ghi

-0.14

bers

-0.14

Ã²i

-0.14

ucz

-0.14

vais

-0.14

POSITIVE LOGITS

 Huss

0.15

oting

0.15

\grid

0.14

clid

0.14

ÑĸÑĩ

0.14

elter

0.14

ymbol

0.14

Ã¡z

0.13

fromJson

0.13

Ã¼ss

0.13

Activations Density 0.044%

geographic or historical references related to places

No Comments

No Known Activations