INDEX

Explanations

references to meals and food experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 initial

-0.17

adera

-0.17

yers

-0.16

lage

-0.16

inn

-0.15

onto

-0.15

ÙĩÙĨ

-0.14

ewater

-0.14

initial

-0.14

POSITIVE LOGITS

izon

0.15

è´¸

0.15

itere

0.14

moduleId

0.14

gni

0.14

afil

0.14

tracker

0.14

 Hundred

0.14

tracking

0.14

oret

0.14

Activations Density 0.006%

references to meals and food experiences

No Comments

No Known Activations