INDEX

Explanations

keywords related to actions, emotions, and various types of media or formats

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

holm

-0.16

 spiked

-0.15

_drv

-0.15

 Spotlight

-0.14

à¹īà¸²à¸ĩ

-0.14

 balloon

-0.14

 Pilot

-0.14

 Rocks

-0.14

 Hello

-0.13

 Spect

-0.13

POSITIVE LOGITS

-fetch

0.17

-mf

0.16

aye

0.16

 labore

0.16

aho

0.15

ÑĨÐ¸Ð¿

0.15

hread

0.15

ummer

0.15

eshire

0.15

ÙĦØ³ÙĦ

0.14

Activations Density 0.061%

keywords related to actions, emotions, and various types of media or formats

No Comments

No Known Activations