INDEX

Explanations

references to metal music genres and styles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Glas

-0.15

eda

-0.15

iller

-0.14

Tib

-0.14

pst

-0.14

yÅ¡

-0.14

æĮĤ

-0.14

 Hubb

-0.14

edin

-0.14

POSITIVE LOGITS

ict

0.16

Specifier

0.16

à¸¢à¸ĩ

0.15

æĤ£

0.15

 hava

0.14

riz

0.14

ikt

0.14

 habitat

0.14

Alv

0.14

.Plugin

0.14

Activations Density 0.007%

references to metal music genres and styles

No Comments

No Known Activations