INDEX

Explanations

phrases related to political statements and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

itle

-0.17

itches

-0.15

eniable

-0.15

reon

-0.15

ardon

-0.15

enz

-0.15

ifix

-0.14

agas

-0.14

utor

-0.14

ëį

-0.14

POSITIVE LOGITS

Wunused

0.15

.docs

0.15

aisal

0.15

adr

0.15

adece

0.15

Wy

0.15

etas

0.15

aji

0.14

 bluff

0.14

Activations Density 0.240%

phrases related to political statements and their implications

No Comments

No Known Activations