INDEX

Explanations

terms related to motor vehicles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

mare

-0.17

ens

-0.17

mir

-0.17

faction

-0.17

eno

-0.16

tf

-0.16

eners

-0.16

ego

-0.16

ure

-0.16

POSITIVE LOGITS

ized

0.33

ised

0.26

cycl

0.25

cade

0.24

OLA

0.22

olla

0.22

bike

0.22

vation

0.22

izations

0.21

ISED

0.21

Activations Density 0.010%

terms related to motor vehicles

No Comments

No Known Activations