INDEX

Explanations

technical terminology related to programming and API structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

éĬ

-0.14

 Crate

-0.14

zac

-0.14

 Knot

-0.14

toPromise

-0.14

 Wend

-0.14

Ð²ÐµÑĤ

-0.13

ä¸ĩåĨĨ

-0.13

ÐµÑĢÐ°ÑĤÑĥ

-0.13

eya

-0.13

POSITIVE LOGITS

 acts

0.22

acts

0.22

 scope

0.21

Dev

0.21

 Acts

0.20

 scopes

0.20

Dev

0.19

Acts

0.19

dev

0.19

_scope

0.19

Activations Density 0.005%

technical terminology related to programming and API structure

No Comments

No Known Activations