INDEX

Explanations

expressions related to personal experiences and reflections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ucas

-0.15

urer

-0.15

aka

-0.15

egan

-0.15

ebra

-0.14

agna

-0.14

nda

-0.14

 incl

-0.13

 sight

-0.13

 recreational

-0.13

POSITIVE LOGITS

adaÅŁ

0.15

 Ã¶rt

0.15

IBE

0.14

pard

0.14

abei

0.14

frey

0.14

inine

0.14

 cá»ĳ

0.14

OAD

0.13

ØªÙĪÙĨ

0.13

Activations Density 0.319%

expressions related to personal experiences and reflections

No Comments

No Known Activations