INDEX

Explanations

references to political leadership and election contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

SSL

-0.18

alama

-0.16

 kontakt

-0.15

ÑĢÐ°Ð²Ð¸

-0.15

enia

-0.15

Offline

-0.14

ÙģÙĤ

-0.14

ICON

-0.14

 IconData

-0.14

SSL

-0.14

POSITIVE LOGITS

Î²Î±

0.16

:animated

0.15

'gc

0.15

 office

0.14

-role

0.14

ante

0.14

<<=

0.14

,module

0.14

ongan

0.13

nested

0.13

Activations Density 0.450%

references to political leadership and election contexts

No Comments

No Known Activations