INDEX

Explanations

descriptions of processes or actions related to guiding or directing activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

roulette

-0.14

onest

-0.14

 plausible

-0.14

uentes

-0.14

inent

-0.14

 Goldberg

-0.14

pie

-0.13

toupper

-0.13

arias

-0.13

inclu

-0.13

POSITIVE LOGITS

 deport

0.17

adaki

0.17

aze

0.16

 organisation

0.15

urer

0.15

 exist

0.15

ude

0.15

".$_

0.15

ught

0.14

{text

0.14

Activations Density 0.050%

descriptions of processes or actions related to guiding or directing activities

No Comments

No Known Activations