INDEX

Explanations

words related to a specific type of dish or food item

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

etter

-0.16

xCD

-0.15

errer

-0.15

 adopt

-0.15

xes

-0.15

herit

-0.15

-0.14

POSITIVE LOGITS

å¹¹ç·ļ

0.16

PHA

0.15

geh

0.15

omid

0.15

folio

0.15

inski

0.15

ihat

0.14

cete

0.14

serter

0.14

ody

0.14

Activations Density 0.002%

words related to a specific type of dish or food item

No Comments

No Known Activations