INDEX

Explanations

specific geographic locations and states or provinces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

-0.14

tures

-0.13

ont

-0.13

sed

-0.13

sed

-0.13

afa

-0.13

ridge

-0.13

hq

-0.13

air

-0.13

ingly

-0.12

POSITIVE LOGITS

utzer

0.15

MMdd

0.15

stor

0.15

spir

0.15

oppel

0.14

ereum

0.14

BOOLE

0.14

eyim

0.14

ominated

0.14

ï¸ı

0.14

Activations Density 0.052%

specific geographic locations and states or provinces

No Comments

No Known Activations