INDEX

Explanations

terms related to food and dining experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

overy

-0.16

auer

-0.15

habit

-0.15

itur

-0.14

.Toolkit

-0.14

_MI

-0.14

kup

-0.14

allon

-0.14

acio

-0.14

POSITIVE LOGITS

&t

0.15

Ø´ÙĪ

0.15

ycz

0.14

-house

0.14

 Russo

0.14

enc

0.14

our

0.13

 choice

0.13

 special

0.13

Activations Density 0.023%

terms related to food and dining experiences

No Comments

No Known Activations