INDEX

Explanations

elements related to perception and awareness in various 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isible

-0.17

ysl

-0.16

 NÄĽk

-0.15

 Clifford

-0.15

rove

-0.15

ãĥ«ãĥĪ

-0.15

iple

-0.14

ç¢°

-0.14

aro

-0.14

ebra

-0.14

POSITIVE LOGITS

esan

0.15

 MÃ£

0.15

FILTER

0.14

 Hakk

0.14

Pes

0.14

-deals

0.14

 EXEMPLARY

0.14

 Field

0.14

akov

0.14

 Kendrick

0.14

Activations Density 0.274%

elements related to perception and awareness in various contexts

No Comments

No Known Activations