INDEX

Explanations

mentions of the character "Ram" from the Ramayana or related contexts

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

emit

-0.20

edo

-0.15

ë¹Ī

-0.15

çłģ

-0.15

ChangedEventArgs

-0.14

vest

-0.14

Ã©gor

-0.14

 Walnut

-0.14

Sez

-0.14

idores

-0.13

POSITIVE LOGITS

aging

0.16

ftype

0.15

ounty

0.14

æĪ²

0.14

Vor

0.14

agon

0.14

aged

0.13

angkan

0.13

Activations Density 0.006%

mentions of the character "Ram" from the Ramayana or related contexts

No Comments

No Known Activations