INDEX

Explanations

instances of the word "literacy" and its variations, indicating a focus on literacy-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ama

-0.16

-uri

-0.16

 Attendance

-0.15

 Sind

-0.15

Å¡ek

-0.15

ointment

-0.14

Attendance

-0.14

TEE

-0.14

sv

-0.14

 Flash

-0.14

POSITIVE LOGITS

zet

0.15

pez

0.15

edla

0.14

CursorPosition

0.14

isnan

0.14

ause

0.14

 Pazar

0.14

ACES

0.14

 CDDL

0.14

Ð¿Ðµ

0.14

Activations Density 0.005%

instances of the word "literacy" and its variations, indicating a focus on literacy-related topics

No Comments

No Known Activations