INDEX

Explanations

references to academic or research-related content

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

natural

-0.15

Disposable

-0.14

istani

-0.14

LETE

-0.14

isphere

-0.14

ãĤĤãĤĬ

-0.14

éŃĤ

-0.14

Natural

-0.14

Ð°ÑĤÐ¸

-0.14

POSITIVE LOGITS

essel

0.15

rans

0.15

é½

0.14

ocks

0.14

stp

0.14

 Lantern

0.14

asn

0.14

endas

0.14

ÑĩÐ¸Ð½Ð¸

0.14

Activations Density 0.094%

references to academic or research-related content

No Comments

No Known Activations