INDEX

Explanations

instances of actions and consequences 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 @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

.springboot

-0.16

tdown

-0.14

Ð»Ñı

-0.14

ermann

-0.14

erosis

-0.14

ufen

-0.14

zat

-0.14

itele

-0.14

aukee

-0.14

Ð·Ð´

-0.14

POSITIVE LOGITS

BuilderInterface

0.14

,strlen

0.14

ãĥ¼ãĥį

0.13

æīį

0.13

 Lane

0.13

abr

0.13

CAPE

0.12

 nackte

0.12

Tee

0.12

(strpos

0.12

Activations Density 0.016%

instances of actions and consequences in narratives

No Comments

No Known Activations