INDEX

Explanations

phrases related to live events and ongoing news coverage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

orea

-0.14

ova

-0.14

assa

-0.14

 Offline

-0.14

omentum

-0.14

IFO

-0.14

ajan

-0.13

anda

-0.13

 builtin

-0.13

 Davidson

-0.13

POSITIVE LOGITS

ÃŃme

0.16

jac

0.15

kre

0.15

 Starr

0.14

 stare

0.14

vinc

0.14

 quar

0.14

levant

0.14

endregion

0.14

aac

0.14

Activations Density 0.021%

phrases related to live events and ongoing news coverage

No Comments

No Known Activations