INDEX

Explanations

references to specific characters and plot elements in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

anna

-0.17

emmel

-0.15

culos

-0.15

sted

-0.14

 hecho

-0.14

cient

-0.14

do

-0.14

weg

-0.13

 sacrifice

-0.13

ea

-0.13

POSITIVE LOGITS

 mesma

0.19

que

0.19

sua

0.18

qui

0.18

inda

0.18

 Ã©p

0.18

ugins

0.17

ÃŃ

0.17

 prÃ³p

0.16

eron

0.16

Activations Density 0.009%

references to specific characters and plot elements in a narrative context

No Comments

No Known Activations