INDEX

Explanations

terms related to documentation and historical themes in art

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 éĹ

-0.15

hiba

-0.15

 Christoph

-0.14

inos

-0.14

elah

-0.14

 flags

-0.14

 twin

-0.13

 Twin

-0.13

 symp

-0.13

SRC

-0.13

POSITIVE LOGITS

edes

0.15

ume

0.15

-ng

0.15

ulen

0.15

odia

0.15

jen

0.15

orex

0.15

opoulos

0.14

Ã¼hl

0.14

WARDS

0.14

Activations Density 0.101%

terms related to documentation and historical themes in art

No Comments

No Known Activations