INDEX

Explanations

character names and significant events 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 @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Sing

-0.16

ÐµÑĤÐµÐ»ÑĮ

-0.16

 Garland

-0.15

MIC

-0.15

å½¹

-0.15

illon

-0.14

ijke

-0.14

 Guidelines

-0.14

 Ging

-0.14

Ã¤tz

-0.14

POSITIVE LOGITS

 ÐŁÐ¾Ð¼

0.15

alth

0.15

ATUS

0.15

 ListViewItem

0.15

atus

0.14

achts

0.14

 sublic

0.14

 kariy

0.14

anh

0.14

ÑģÐ¾Ð»

0.14

Activations Density 0.357%

character names and significant events in narratives

No Comments

No Known Activations