INDEX

Explanations

predictions or discussions about wrestling events and match outcomes

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

pong

-0.15

ÅĽÄĩ

-0.15

TEGER

-0.15

hea

-0.15

Ð¢Ðŀ

-0.15

dea

-0.14

ãĥ¼ãĤ¹

-0.14

amarin

-0.14

hlas

-0.14

IKE

-0.14

POSITIVE LOGITS

 Sous

0.16

iga

0.15

0.14

 Latter

0.14

uns

0.13

erts

0.13

ished

0.13

atus

0.13

 mach

0.13

Activations Density 0.087%

predictions or discussions about wrestling events and match outcomes

No Comments

No Known Activations