INDEX

Explanations

mentions of specific U.S. states, particularly Florida and California

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

æĹ

-0.18

aria

-0.15

ucks

-0.15

 Cumhuriyet

-0.14

Clr

-0.14

aml

-0.14

 sooner

-0.14

_unpack

-0.13

/downloads

-0.13

fas

-0.13

POSITIVE LOGITS

avior

0.16

cke

0.15

kie

0.15

eck

0.15

chein

0.15

aviour

0.15

chest

0.15

ãĥ»ãĤ¢

0.14

anka

0.14

itre

0.14

Activations Density 0.023%

mentions of specific U.S. states, particularly Florida and California

No Comments

No Known Activations