INDEX

Explanations

references to certification, qualification, or professional development programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

-0.24

os

-0.24

len

-0.22

erd

-0.21

erp

-0.20

ro

-0.20

roc

-0.19

ln

-0.18

eras

-0.18

hm

-0.18

POSITIVE LOGITS

duk

0.18

dete

0.18

CTSTR

0.17

ritch

0.17

DL

0.16

 Carey

0.16

ilogue

0.15

fÃ¼

0.15

Ds

0.15

rior

0.15

Activations Density 0.046%

references to certification, qualification, or professional development programs

No Comments

No Known Activations