INDEX

Explanations

references to templates and their usage in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ucid

-0.16

ude

-0.16

onders

-0.15

udy

-0.15

ivÃ©

-0.15

arshal

-0.15

ioni

-0.15

ioneer

-0.15

arin

-0.14

POSITIVE LOGITS

typ

0.31

typename

0.29

(typ

0.29

<typename

0.29

 typename

0.29

.typ

0.25

Fen

0.24

fen

0.23

typ

0.23

 phen

0.23

Activations Density 0.001%

references to templates and their usage in programming contexts

No Comments

No Known Activations