INDEX

Explanations

references to government entities and organizational structures

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_states

-0.22

 states

-0.20

 States

-0.20

_STATES

-0.19

.states

-0.19

states

-0.19

States

-0.19

-states

-0.18

 statements

-0.17

Statements

-0.17

POSITIVE LOGITS

 municipal

0.23

 city

0.22

 local

0.21

 territory

0.20

 tribal

0.20

 territories

0.20

 Tribal

0.20

 Trib

0.20

city

0.20

 county

0.19

Activations Density 0.029%

references to government entities and organizational structures

No Comments

No Known Activations