INDEX

Explanations

terms related to political and military context in Lebanon

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

amo

-0.15

ENDOR

-0.14

EdgeInsets

-0.14

amazon

-0.14

quet

-0.14

_Native

-0.14

amu

-0.14

bond

-0.14

lectron

-0.14

endencies

-0.14

POSITIVE LOGITS

ÏĨÎ¹

0.14

angers

0.14

 Levine

0.14

 Paras

0.14

 Herc

0.13

RAIN

0.13

alm

0.13

prox

0.13

tru

0.13

Activations Density 0.024%

terms related to political and military context in Lebanon

No Comments

No Known Activations