INDEX

Explanations

references to specific scenes and sequences 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 @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

orna

-0.17

rowable

-0.15

ustos

-0.15

CEED

-0.14

orny

-0.14

ceeded

-0.14

-toggler

-0.13

erus

-0.13

ificacion

-0.13

serial

-0.13

POSITIVE LOGITS

umann

0.17

ikon

0.15

ieu

0.14

 Hodg

0.14

 floating

0.14

 comparator

0.14

Ã©p

0.14

erald

0.14

 Katz

0.14

exchange

0.13

Activations Density 0.072%

references to specific scenes and sequences in a narrative context

No Comments

No Known Activations