INDEX

Explanations

programming functions and method definitions related to data parsing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ONENT

-0.19

ija

-0.18

anes

-0.15

leton

-0.14

liÅ¡

-0.14

inear

-0.14

uliar

-0.14

Ø¬ÙĨ

-0.14

VL

-0.13

 ãĥ´

-0.13

POSITIVE LOGITS

Cle

0.16

gt

0.16

cle

0.15

[](

0.15

cle

0.15

gg

0.14

åĢ

0.14

rama

0.14

 Mond

0.14

USTOM

0.14

Activations Density 0.015%

programming functions and method definitions related to data parsing

No Comments

No Known Activations