INDEX

Explanations

references to various forms of written and spoken content, particularly in relation to legal or academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Ł

-0.16

Ø´Ùħ

-0.16

opoulos

-0.15

reib

-0.15

ìĦĿ

-0.15

kah

-0.15

igy

-0.14

VP

-0.14

ock

-0.14

ÙĪÙĦÙĩ

-0.14

POSITIVE LOGITS

hread

0.16

irth

0.15

rain

0.15

ia

0.15

hed

0.15

amar

0.14

IA

0.14

iant

0.14

raz

0.14

 bÃ©nÃ©

0.14

Activations Density 0.037%

references to various forms of written and spoken content, particularly in relation to legal or academic contexts

No Comments

No Known Activations