INDEX

Explanations

elements of mystery or suspense 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

anken

-0.16

ERRU

-0.15

erosis

-0.15

Å¯

-0.15

taboola

-0.14

toi

-0.14

ystack

-0.14

elong

-0.14

bject

-0.14

etten

-0.14

POSITIVE LOGITS

 main

0.16

upt

0.16

ens

0.16

 Detective

0.16

 Call

0.15

 Cord

0.15

 Officer

0.15

 Bliss

0.15

FBI

0.15

 Hutch

0.14

Activations Density 0.504%

elements of mystery or suspense in narratives

No Comments

No Known Activations