INDEX

Explanations

reflections on decision-making and planning 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

umo

-0.16

.FontStyle

-0.16

gle

-0.15

hle

-0.15

ogenous

-0.14

vero

-0.14

osg

-0.14

afe

-0.14

lements

-0.14

eyen

-0.14

POSITIVE LOGITS

æĹ¢çĦ¶

0.18

 ought

0.16

heck

0.16

haps

0.16

might

0.15

 best

0.15

best

0.15

 since

0.14

since

0.14

 might

0.14

Activations Density 0.079%

reflections on decision-making and planning processes

No Comments

No Known Activations