INDEX

Explanations

gerunds or present participles indicating ongoing actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

/remove

-0.25

ings

-0.23

ÂŃing

-0.18

/write

-0.18

veloper

-0.17

INGS

-0.17

/disable

-0.17

/close

-0.17

/run

-0.17

/delete

-0.16

POSITIVE LOGITS

ly

0.31

/testing

0.21

/loading

0.21

/logging

0.18

LY

0.18

 oneself

0.18

/up

0.17

ny

0.17

ness

0.16

/rem

0.16

Activations Density 1.292%

gerunds or present participles indicating ongoing actions or processes

No Comments

No Known Activations