INDEX

Explanations

references to programming frameworks and libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

rig

-0.15

otoxic

-0.14

mi

-0.14

 Caldwell

-0.14

ync

-0.14

arro

-0.14

Fig

-0.14

pac

-0.13

 express

-0.13

POSITIVE LOGITS

ãĥ³ãĤº

0.16

Ð²ÐµÑģÑĤ

0.16

oslav

0.15

gnore

0.14

voie

0.14

 ÙĥÙĨØ¯

0.14

Ø³ØªØ§ÙĨ

0.14

_elim

0.14

 addCriterion

0.14

://'

0.13

Activations Density 0.008%

references to programming frameworks and libraries

No Comments

No Known Activations