INDEX

Explanations

numerical data and related calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

âĢ¦↵

-0.17

-0.15

urat

-0.14

 âĢ¦↵

-0.14

 [âĢ¦]↵

-0.13

Deb

-0.13

afi

-0.12

 Nath

-0.12

inox

-0.12

rees

-0.12

POSITIVE LOGITS

/tos

0.16

leftright

0.15

IEW

0.14

flen

0.14

OGRAPH

0.14

 oppon

0.13

Detach

0.13

 sona

0.13

.WinForms

0.13

/frontend

0.13

Activations Density 0.528%

numerical data and related calculations

No Comments

No Known Activations