INDEX

Explanations

references to social hierarchy 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 @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

enheim

-0.19

 Administrative

-0.17

 wrongdoing

-0.16

.documentation

-0.15

 Protective

-0.15

 Typed

-0.15

folk

-0.15

 exceptionally

-0.15

 Stevenson

-0.15

 deterrent

-0.15

POSITIVE LOGITS

oe

0.19

 publicly

0.18

 domest

0.18

 Åĵ

0.16

OPS

0.16

 late

0.16

ÌĨ

0.15

zel

0.15

 british

0.15

 uncommon

0.15

Activations Density 0.064%

references to social hierarchy and relationships

No Comments

No Known Activations