INDEX

Explanations

words and phrases related to adjectives and their usage in modifying nouns

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

abad

-0.15

anz

-0.14

LAB

-0.14

bob

-0.14

 Made

-0.14

 made

-0.13

oub

-0.13

itia

-0.13

 Reserved

-0.13

omap

-0.13

POSITIVE LOGITS

 targeted

0.29

 target

0.28

target

0.25

 ÙħÙĪØ±Ø¯

0.24

 targ

0.23

 targets

0.23

covered

0.21

-target

0.21

Target

0.21

 involved

0.21

Activations Density 0.291%

words and phrases related to adjectives and their usage in modifying nouns

No Comments

No Known Activations