INDEX

Explanations

entities related to legal and governmental titles or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ntag

-0.14

ãĥ¼ãĥĭ

-0.13

ohl

-0.13

dbContext

-0.13

ocab

-0.12

 pione

-0.12

eam

-0.12

romise

-0.12

_argv

-0.12

ufe

-0.12

POSITIVE LOGITS

 general

1.31

 General

1.22

general

1.16

General

1.12

-general

1.09

 GENERAL

1.09

 gÃ©nÃ©ral

1.00

_general

0.98

-General

0.94

GENERAL

0.94

Activations Density 0.301%

entities related to legal and governmental titles or positions

No Comments

No Known Activations