INDEX

Explanations

references to specific brands or products, particularly in the context of consumer goods

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

merce

-0.14

 ÑģÐµÑĤ

-0.14

ancement

-0.14

oya

-0.14

 Franti

-0.14

enty

-0.13

jar

-0.13

TEGER

-0.13

ngine

-0.13

lijke

-0.13

POSITIVE LOGITS

roz

0.18

angle

0.16

å§¿

0.16

alis

0.15

stru

0.15

ipa

0.14

ridge

0.14

æī£

0.14

/rc

0.14

ache

0.14

Activations Density 0.009%

references to specific brands or products, particularly in the context of consumer goods

No Comments

No Known Activations