INDEX

Explanations

references to cooking utensils, containers, and preparation measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ÏĦÎ¿Ïį

-0.15

VML

-0.15

iteli

-0.15

Ð¾Ð·Ð¸

-0.14

allest

-0.14

arel

-0.14

åŀĤ

-0.14

arte

-0.14

emi

-0.14

arde

-0.14

POSITIVE LOGITS

liner

0.18

nder

0.16

 fitted

0.15

psy

0.15

ifen

0.15

 bowl

0.14

NDER

0.14

 pref

0.14

 Pour

0.14

stan

0.14

Activations Density 0.014%

references to cooking utensils, containers, and preparation measurements

No Comments

No Known Activations