INDEX

Explanations

references to government officials and their titles

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

StandardItem

-0.18

yd

-0.16

SharedPointer

-0.15

ksam

-0.15

abo

-0.15

ÏĦÎŃÎ»Îµ

-0.15

abis

-0.15

abwe

-0.15

umni

-0.14

 Ãºn

-0.14

POSITIVE LOGITS

ial

0.21

 Responsible

0.15

ToLocal

0.15

undles

0.15

embre

0.14

MOTE

0.14

ube

0.14

omatic

0.14

IAL

0.14

.Names

0.14

Activations Density 0.028%

references to government officials and their titles

No Comments

No Known Activations