INDEX

Explanations

references to alternatives or other options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

shaw

-0.16

ijk

-0.16

oux

-0.15

rab

-0.15

rade

-0.15

eler

-0.14

wap

-0.14

ler

-0.14

evice

-0.14

à¹Ģà¸Ńà¸ĩ

-0.14

POSITIVE LOGITS

urdy

0.15

 than

0.15

_than

0.14

iline

0.14

-than

0.14

 Detector

0.14

jes

0.14

isle

0.14

kes

0.14

integral

0.13

Activations Density 0.018%

references to alternatives or other options

No Comments

No Known Activations