INDEX

Explanations

terms related to family and relationships

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

elow

-0.18

 Marketable

-0.15

eln

-0.14

andi

-0.14

\Carbon

-0.14

ylene

-0.14

 Lowe

-0.14

ousse

-0.14

-net

-0.13

issor

-0.13

POSITIVE LOGITS

 Ð¶Ð¸ÑĢ

0.16

RATION

0.14

cano

0.14

orda

0.14

 Talking

0.13

summ

0.13

MainFrame

0.13

 disadv

0.13

-ok

0.13

roducing

0.13

Activations Density 0.007%

terms related to family and relationships

No Comments

No Known Activations