INDEX

Explanations

elements related to character relationships and dynamics in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

hsi

-0.16

arel

-0.15

æĹıèĩªæ²»

-0.15

_ALIGN

-0.15

aina

-0.14

-yyyy

-0.14

rray

-0.14

å¡ļ

-0.14

HeaderCode

-0.14

ä¸ĭåİ»

-0.14

POSITIVE LOGITS

 (“

0.15

Ä±zÄ±

0.15

 Roth

0.14

 whom

0.13

itle

0.13

 Bishop

0.13

 Harris

0.13

 whose

0.13

 Kirk

0.13

Activations Density 0.152%

elements related to character relationships and dynamics in narratives

No Comments

No Known Activations