INDEX

Explanations

mathematical equations and alignments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

arel

-0.17

rov

-0.16

Cru

-0.14

Neb

-0.14

stood

-0.14

div

-0.14

ma

-0.14

othy

-0.13

roc

-0.13

POSITIVE LOGITS

0.16

Sok

0.15

imity

0.15

athom

0.15

hg

0.14

ë¦¬ìĸ´

0.13

ime

0.13

Fam

0.13

ipse

0.13

ãģĶ

0.13

Activations Density 0.029%

mathematical equations and alignments

No Comments

No Known Activations

mathematical equations and alignments

No Comments

No Known Activations