INDEX

Explanations

references to photography and photographers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

filer

-0.16

ief

-0.16

orama

-0.15

ensburg

-0.14

ä¼ł

-0.14

\application

-0.14

 instanceof

-0.14

 Cust

-0.14

spell

-0.13

nga

-0.13

POSITIVE LOGITS

lech

0.16

yen

0.16

irket

0.14

ovies

0.14

thesis

0.13

Fld

0.13

 Flint

0.13

Ä±nÄ±f

0.13

.struts

0.13

extField

0.13

Activations Density 0.060%

references to photography and photographers

No Comments

No Known Activations