INDEX

Explanations

references to specific products or models, particularly kitchen appliances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ottle

-0.15

 éĢ

-0.14

ollo

-0.14

GBK

-0.14

fono

-0.14

Arm

-0.14

eur

-0.14

 autof

-0.14

lao

-0.14

-0.13

POSITIVE LOGITS

stered

0.16

kola

0.15

LAG

0.14

hausen

0.14

inda

0.13

ï»¿#

0.13

arger

0.13

unde

0.13

quiring

0.13

CLK

0.13

Activations Density 0.497%

references to specific products or models, particularly kitchen appliances

No Comments

No Known Activations