INDEX

Explanations

references to art exhibitions and influential artists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

csi

-0.18

 Newspaper

-0.16

äº

-0.16

ilor

-0.15

onen

-0.15

OPLE

-0.15

oogle

-0.14

zi

-0.14

phants

-0.14

uta

-0.14

POSITIVE LOGITS

 talent

0.20

 talents

0.18

 local

0.15

 talented

0.15

/auth

0.15

 quis

0.15

 contemporary

0.14

 gere

0.14

OID

0.14

 emerging

0.14

Activations Density 0.108%

references to art exhibitions and influential artists

No Comments

No Known Activations