INDEX

Explanations

instances of accountability and relationship dynamics among characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ÎµÎ½

-0.14

AGO

-0.14

 opposite

-0.13

 Sommer

-0.13

ea

-0.13

.dsl

-0.13

avier

-0.13

agna

-0.13

agus

-0.13

ander

-0.13

POSITIVE LOGITS

nek

0.14

 Moor

0.14

-prepend

0.14

/cop

0.14

-scrollbar

0.14

ilon

0.14

opies

0.14

apan

0.14

ipsis

0.13

umpt

0.13

Activations Density 0.925%

instances of accountability and relationship dynamics among characters

No Comments

No Known Activations