INDEX

Explanations

references to religious groups and their affiliations

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

.appspot

-0.16

 hete

-0.15

reff

-0.15

 nÃ¦r

-0.15

.RequestMethod

-0.14

êµ´

-0.14

-js

-0.14

nets

-0.14

utsch

-0.14

Tos

-0.14

POSITIVE LOGITS

 boxed

0.14

Alf

0.14

/MPL

0.14

 inclined

0.14

airro

0.14

 poster

0.14

Chr

0.13

HTTPHeader

0.13

-Sah

0.13

 rtrim

0.13

Activations Density 0.060%

references to religious groups and their affiliations

No Comments

No Known Activations