INDEX

Explanations

references to political leadership and election processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ÑĢÐ°Ð¹

-0.15

áº§m

-0.15

atron

-0.15

ritt

-0.14

agan

-0.14

_partial

-0.14

awl

-0.14

 discrete

-0.14

æ¸¯

-0.14

POSITIVE LOGITS

ÛĮØ²ÛĮ

0.14

uars

0.14

izont

0.14

 belie

0.14

ÑĨÐ¸Ð½

0.14

kip

0.14

PathComponent

0.14

nested

0.14

ìĭ¬

0.14

lik

0.14

Activations Density 0.042%

references to political leadership and election processes

No Comments

No Known Activations