INDEX

Explanations

phrases indicating critique or negative assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ð»Ð¸Ð²

-0.18

pyx

-0.17

icht

-0.16

uren

-0.15

ubl

-0.15

nnen

-0.15

 PÅĻi

-0.15

andre

-0.15

 Pipe

-0.14

odon

-0.14

POSITIVE LOGITS

yscale

0.17

outil

0.16

.spin

0.15

aleza

0.14

angel

0.14

 Chance

0.14

OrNull

0.14

YD

0.14

Äħd

0.13

ergus

0.13

Activations Density 0.018%

phrases indicating critique or negative assessments

No Comments

No Known Activations