INDEX

Explanations

specific cases and instances related to truth and validity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ÑīÐ¸Ð½

-0.16

oup

-0.15

oras

-0.14

roup

-0.14

pio

-0.14

.Sdk

-0.14

abar

-0.13

ker

-0.13

asto

-0.13

Ã¼f

-0.13

POSITIVE LOGITS

 chez

0.25

 when

0.22

 elsewhere

0.19

 whenever

0.19

å¯¹äºİ

0.18

à¸ªà¸³à¸«à¸£

0.16

 everywhere

0.15

for

0.15

 Äĳá»ĳi

0.15

ANGER

0.15

Activations Density 0.271%

specific cases and instances related to truth and validity

No Comments

No Known Activations