INDEX

Explanations

references to the number eight

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ëį°

-0.25

ait

-0.19

ings

-0.19

ibus

-0.15

ª

-0.15

iegel

-0.15

adox

-0.15

rtle

-0.15

shi

-0.15

ORIZONTAL

-0.15

POSITIVE LOGITS

eenth

0.41

een

0.38

0.18

ï¸ı

0.18

../../

0.17

th

0.16

Ð±Ð¸ÑĤ

0.16

bis

0.15

âĢ³

0.14

bpp

0.14

Activations Density 0.368%

references to the number eight

No Comments

No Known Activations