INDEX

Explanations

prominent personal pronouns and expressions of emotional engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

icho

-0.16

odem

-0.16

onis

-0.15

ersistence

-0.15

Ã¤re

-0.14

Ã£y

-0.14

thouse

-0.14

ayment

-0.14

inth

-0.14

uento

-0.14

POSITIVE LOGITS

istrat

0.14

.synthetic

0.14

roman

0.14

_mB

0.14

æľŃ

0.13

ENDOR

0.13

 stacks

0.13

Spo

0.13

ERTICAL

0.13

Activations Density 0.178%

prominent personal pronouns and expressions of emotional engagement

No Comments

No Known Activations