INDEX

Explanations

words related to content organization and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

EMPL

-0.15

pedo

-0.15

stash

-0.14

asd

-0.14

_PAD

-0.14

InputStream

-0.14

chartInstance

-0.14

ÑĥÐ½Ðº

-0.13

 è¨

-0.13

stration

-0.13

POSITIVE LOGITS

/out

0.24

TargetException

0.17

 gramm

0.17

iliz

0.17

-Out

0.17

ãģ£ãģ

0.15

achment

0.15

ÎŃÏģÎ³

0.15

/ex

0.15

Activations Density 0.116%

words related to content organization and structure

No Comments

No Known Activations