INDEX

Explanations

references to government and political entities

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

otope

-0.14

viders

-0.14

elerik

-0.14

Ŀi

-0.14

IAS

-0.13

vars

-0.13

engu

-0.13

CV

-0.13

umerator

-0.13

POSITIVE LOGITS

gether

0.16

etheless

0.15

ome

0.15

ollen

0.14

adays

0.14

 Square

0.14

uve

0.14

rant

0.14

 Weston

0.14

olah

0.13

Activations Density 0.350%

references to government and political entities

No Comments

No Known Activations