INDEX

Explanations

references to legal processes and procedures

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

 downs

-0.17

 resett

-0.16

 personalised

-0.15

 discrim

-0.15

Sol

-0.15

 revis

-0.15

 travers

-0.15

 elabor

-0.14

nud

-0.14

wa

-0.14

POSITIVE LOGITS

Use

0.18

eph

0.18

Use

0.17

 become

0.17

Use

0.17

Put

0.16

 start

0.15

Set

0.15

put

0.15

Get

0.15

Activations Density 0.282%

references to legal processes and procedures

No Comments

No Known Activations