INDEX

Explanations

references to programming and markup language elements or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

czy

-0.15

 presentation

-0.14

 Crosby

-0.14

irc

-0.14

than

-0.13

egov

-0.13

cons

-0.13

ERGE

-0.13

/oauth

-0.13

 Presentation

-0.13

POSITIVE LOGITS

ãĥªãĥ¼ãĤº

0.15

_putstr

0.14

lix

0.14

olec

0.14

yy

0.14

amera

0.14

-fw

0.14

ogui

0.14

queeze

0.13

enek

0.13

Activations Density 0.437%

references to programming and markup language elements or structures

No Comments

No Known Activations