INDEX

Explanations

phrases related to governmental and legal authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

legalArgumentException

-0.15

 fastball

-0.13

amura

-0.12

pei

-0.12

 è©

-0.12

.TabStop

-0.12

ajo

-0.11

Ø¶Ø©

-0.11

Countries

-0.11

elp

-0.11

POSITIVE LOGITS

 state

1.38

state

1.17

 State

1.16

-state

1.09

State

1.02

_state

1.02

.state

0.98

 STATE

0.95

(state

0.93

	state

0.85

Activations Density 0.476%

phrases related to governmental and legal authority

No Comments

No Known Activations