INDEX

Explanations

specific terms related to legal issues or court proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

kem

-0.16

ello

-0.15

tal

-0.14

idge

-0.14

ischer

-0.14

nat

-0.14

endor

-0.14

izz

-0.14

 Cliff

-0.14

POSITIVE LOGITS

ÏĩÏĮ

0.15

Ð¾Ð¹Ð½Ð¾

0.15

ÑĮÑİÑĤ

0.15

getDisplay

0.14

pec

0.14

 prolong

0.14

hlen

0.14

culus

0.14

 hints

0.14

Activations Density 0.007%

specific terms related to legal issues or court proceedings

No Comments

No Known Activations