INDEX

Explanations

references to certification and 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

enheim

-0.17

ly

-0.17

roc

-0.17

opian

-0.16

Å¾

-0.15

abin

-0.15

idget

-0.15

osal

-0.15

hn

-0.15

Å¾e

-0.15

POSITIVE LOGITS

ufreq

0.18

ocab

0.17

.deepcopy

0.16

dete

0.16

 Rail

0.15

CP

0.15

cp

0.15

ahl

0.15

cp

0.14

uset

0.14

Activations Density 0.013%

references to certification and professional development programs

No Comments

No Known Activations