INDEX

Explanations

references to notable people, places, and entities in contexts related to prominence and recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

PMC

-0.17

apter

-0.16

 Plantae

-0.15

OKIE

-0.15

elman

-0.15

ebb

-0.14

abd

-0.14

agal

-0.14

.routes

-0.14

éĲ

-0.14

POSITIVE LOGITS

 called

0.18

geh

0.16

ordinate

0.15

alty

0.15

ines

0.15

ativity

0.14

 actu

0.14

ãģ§ãģĤãĤĭ

0.14

Activations Density 0.124%

references to notable people, places, and entities in contexts related to prominence and recognition

No Comments

No Known Activations