INDEX

Explanations

references to fuel-related topics, particularly petrol and gasoline usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

kas

-0.15

Ã¢m

-0.15

oda

-0.15

etty

-0.14

elor

-0.14

Ass

-0.14

ures

-0.14

izen

-0.13

reen

-0.13

rys

-0.13

POSITIVE LOGITS

erate

0.17

ehler

0.16

ãĤ¸ãĤ¢

0.16

ccione

0.15

asje

0.15

igu

0.15

 Admir

0.15

headed

0.14

ccion

0.14

Separated

0.14

Activations Density 0.027%

references to fuel-related topics, particularly petrol and gasoline usage

No Comments

No Known Activations