INDEX

Explanations

mathematical expressions and probabilities

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

Sort

-0.16

/browse

-0.16

rank

-0.15

 Measure

-0.15

 Fork

-0.14

å§Ķ

-0.14

ixin

-0.14

isku

-0.14

anke

-0.14

 Dynam

-0.13

POSITIVE LOGITS

 simpl

0.26

 simplify

0.24

wol

0.24

Wol

0.23

 cancel

0.23

 Plug

0.23

 cancelling

0.23

 plug

0.23

Plug

0.23

 Canc

0.23

Activations Density 0.102%

mathematical expressions and probabilities

No Comments

No Known Activations