INDEX

Explanations

references to historical figures or events related to dynasties and power structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

chl

-0.16

oyo

-0.16

.wp

-0.15

/dir

-0.15

ERSION

-0.15

aload

-0.15

ubern

-0.15

tolua

-0.15

regor

-0.14

lian

-0.14

POSITIVE LOGITS

anza

0.15

dup

0.15

 coaches

0.14

bourg

0.14

 news

0.13

Bron

0.13

 coaching

0.13

Tet

0.13

Activations Density 0.038%

references to historical figures or events related to dynasties and power structures

No Comments

No Known Activations