INDEX

Explanations

mentions of family members 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 @ 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

 glGet

-0.16

okers

-0.15

 prÃ¡

-0.14

à¸¸à¸ĩ

-0.14

reste

-0.14

åĮĸ

-0.14

utsch

-0.14

pec

-0.13

ÑĪ

-0.13

POSITIVE LOGITS

.gdx

0.16

 Incorporated

0.15

Ŀ

0.15

.nih

0.15

.objects

0.14

 Burgess

0.14

 Meyer

0.14

 Bernard

0.14

vsp

0.14

Activations Density 0.003%

mentions of family members and relationships

No Comments

No Known Activations