INDEX

Explanations

phrases indicating a necessity for change or improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Ã¤s

-0.17

getc

-0.16

bÃŃ

-0.15

ossa

-0.15

oken

-0.15

elpers

-0.14

uess

-0.14

 intercept

-0.14

gettext

-0.14

isel

-0.14

POSITIVE LOGITS

emiz

0.16

edin

0.15

itol

0.15

åĲĪãĤıãģĽ

0.15

laps

0.15

0.14

OLT

0.14

ungs

0.14

oenix

0.14

urable

0.14

Activations Density 0.002%

phrases indicating a necessity for change or improvement

No Comments

No Known Activations