INDEX

Explanations

proper nouns, particularly associated with religious figures and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

izmet

-0.15

senal

-0.15

ãĤĥ

-0.14

Ã¡tis

-0.14

ince

-0.14

kke

-0.14

pline

-0.14

 WaitForSeconds

-0.13

 Ø±Ùħ

-0.13

-ST

-0.13

POSITIVE LOGITS

Mir

0.16

 intens

0.15

Sau

0.14

áº©n

0.14

 already

0.14

 numbered

0.13

orden

0.13

Gu

0.13

 bite

0.13

Activations Density 0.312%

proper nouns, particularly associated with religious figures and locations

No Comments

No Known Activations