INDEX

Explanations

references to historical figures and scholarly authors

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

eca

-0.15

 knock

-0.15

å®ħ

-0.14

_firestore

-0.14

 Folk

-0.13

áº¯m

-0.13

 è»

-0.13

ITAL

-0.13

ylvania

-0.13

Descriptors

-0.13

POSITIVE LOGITS

orial

0.17

kes

0.16

0.15

ogi

0.15

aged

0.14

dash

0.14

agi

0.14

opp

0.14

age

0.14

ãĤ¹ãĤ¯

0.14

Activations Density 0.118%

references to historical figures and scholarly authors

No Comments

No Known Activations