INDEX

Explanations

mentions of specific locations or geographical names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ewan

-0.18

sworth

-0.18

hti

-0.16

cht

-0.16

ATRIX

-0.16

alcon

-0.15

essen

-0.15

lez

-0.15

meldung

-0.15

POSITIVE LOGITS

ifornia

0.20

antan

0.20

iforn

0.18

bsolute

0.18

ervo

0.16

weit

0.16

antz

0.15

istrat

0.15

Ãºa

0.15

amera

0.15

Activations Density 0.008%

mentions of specific locations or geographical names

No Comments

No Known Activations