INDEX

Explanations

terms related to automotive features and performance specifications

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

Powered

-0.17

ream

-0.15

enzie

-0.15

VIP

-0.14

 cram

-0.14

Conversion

-0.14

¥¤

-0.14

ìĥī

-0.14

ç³»

-0.13

_THREADS

-0.13

POSITIVE LOGITS

 Electronic

0.19

(mode

0.18

 Stability

0.18

 Electron

0.17

 Assist

0.17

 modes

0.17

 limp

0.17

 ACTIVE

0.17

ESS

0.17

Maps

0.17

Activations Density 0.027%

terms related to automotive features and performance specifications

No Comments

No Known Activations