INDEX

Explanations

code documentation and comments regarding function parameters and returns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

iskey

-0.15

xfff

-0.14

 ï¼

-0.13

ourcem

-0.13

½æķ°

-0.13

inyin

-0.13

fdc

-0.13

ERTICAL

-0.13

NotAllowed

-0.13

orges

-0.13

POSITIVE LOGITS

swer

0.17

INET

0.17

strup

0.15

_finalize

0.14

 Cottage

0.14

 extras

0.13

ning

0.13

0.12

,double

0.12

Activations Density 0.110%

code documentation and comments regarding function parameters and returns

No Comments

No Known Activations