INDEX

Explanations

pronouns and their usage in text, indicating a focus on personal or conversational language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 protect

-0.16

ebi

-0.15

 narration

-0.15

Refreshing

-0.14

Backing

-0.14

protect

-0.14

 protection

-0.14

 Protection

-0.14

 guardian

-0.13

Protected

-0.13

POSITIVE LOGITS

iera

0.17

à¥įà¤µà¤ļ

0.17

 Bash

0.16

arrison

0.15

GGLE

0.15

pedia

0.15

 reliance

0.15

tridge

0.15

ancell

0.15

icz

0.15

Activations Density 0.005%

pronouns and their usage in text, indicating a focus on personal or conversational language

No Comments

No Known Activations