INDEX

Explanations

references to documents and coding elements 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 kent

-0.18

oque

-0.16

Ø¯ÙĪØ§Ø¬

-0.15

 Smooth

-0.15

oes

-0.14

 Tribe

-0.14

MOOTH

-0.14

azines

-0.14

oe

-0.14

POSITIVE LOGITS

rito

0.15

nar

0.15

iane

0.15

ÛĮØ¯ÛĮ

0.15

eko

0.15

_tac

0.14

adle

0.14

 Hatch

0.14

¬ģ

0.14

ctl

0.14

Activations Density 0.006%

references to documents and coding elements in programming contexts

No Comments

No Known Activations