INDEX

Explanations

terms related to car models and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

edor

-0.14

alcon

-0.14

 Morr

-0.14

èĬ±

-0.14

_FINAL

-0.13

emos

-0.13

 Glock

-0.13

engeance

-0.13

amo

-0.13

 Canter

-0.13

POSITIVE LOGITS

ouble

0.17

 Ø§ÙĦÙĤØ±ÙĨ

0.15

ãģĵãĤį

0.15

 Khoa

0.15

Ãłi

0.15

_SP

0.14

ingo

0.14

dates

0.14

Trou

0.14

ãģ«è¦ĭ

0.14

Activations Density 0.101%

terms related to car models and their features

No Comments

No Known Activations