INDEX

Explanations

references to academic papers and studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Laud

-0.15

ylland

-0.14

mere

-0.14

omi

-0.14

FieldName

-0.13

iri

-0.13

mom

-0.13

kiem

-0.13

Ã©m

-0.13

éĽ

-0.13

POSITIVE LOGITS

we

0.20

ï¼ĮæĪĳä»¬

0.16

æĪĳä»¬

0.15

 nosotros

0.14

áº±m

0.14

bose

0.14

 Fate

0.14

.effects

0.14

 ìļ°ë¦¬ëĬĶ

0.13

 instead

0.13

Activations Density 0.032%

references to academic papers and studies

No Comments

No Known Activations