INDEX

Explanations

references to interpersonal relationships and social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Ã©ric

-0.14

Ð·Ñı

-0.14

yle

-0.13

ddit

-0.13

furt

-0.13

immers

-0.13

Modifiers

-0.13

adolu

-0.13

okit

-0.13

ournals

-0.13

POSITIVE LOGITS

 friends

0.88

 friend

0.72

æľĭåıĭ

0.66

friends

0.66

 colleagues

0.63

 Friends

0.58

Friends

0.57

 fellow

0.55

 peers

0.55

 FRIEND

0.54

Activations Density 0.175%

references to interpersonal relationships and social interactions

No Comments

No Known Activations