INDEX

Explanations

occurrences of the word "out"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

_output

-0.25

 output

-0.21

argout

-0.20

OUTPUT

-0.19

_outputs

-0.19

 outbreak

-0.19

 outputs

-0.19

Output

-0.19

 outdoor

-0.18

 outstanding

-0.18

POSITIVE LOGITS

wards

0.41

ta

0.38

-of

0.27

land

0.26

lying

0.24

SIDE

0.24

/down

0.24

lander

0.23

ters

0.23

sert

0.23

Activations Density 0.209%

occurrences of the word "out"

No Comments

No Known Activations