INDEX

Explanations

references to lengthy durations and quantifiable measurements related to time and distance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

serrat

-0.15

bo

-0.15

Å¡ak

-0.14

 limp

-0.14

ameda

-0.14

 Pero

-0.14

è¾

-0.14

erea

-0.14

bere

-0.13

POSITIVE LOGITS

kul

0.17

arse

0.15

PCP

0.14

 otom

0.14

Intern

0.14

heid

0.14

ãĥ¼ãĥĹ

0.14

 Carn

0.13

 Raised

0.13

à¸Ħà¸¥

0.13

Activations Density 0.198%

references to lengthy durations and quantifiable measurements related to time and distance

No Comments

No Known Activations