INDEX

Explanations

references to specific individuals or artists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 reim

-0.16

onaut

-0.15

å£ģ

-0.15

rios

-0.15

iks

-0.14

 Clem

-0.14

.OnClickListener

-0.14

eros

-0.14

eya

-0.13

grim

-0.13

POSITIVE LOGITS

 Rust

0.17

LATED

0.16

 timespec

0.16

 vice

0.15

 Podesta

0.15

 âĢİ

0.15

Tun

0.14

 Tanner

0.14

aceut

0.13

 native

0.13

Activations Density 0.006%

references to specific individuals or artists

No Comments

No Known Activations