INDEX

Explanations

U.S. state names and their associations in the text

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

ome

-0.15

etwork

-0.15

upa

-0.15

Bush

-0.15

wa

-0.14

 Blur

-0.14

arm

-0.14

↵

-0.14

idelity

-0.14

Rob

-0.14

POSITIVE LOGITS

 Kurulu

0.16

 zoekt

0.16

uisse

0.16

SGlobal

0.14

iona

0.14

 Ripple

0.14

 ylim

0.14

vÄĽ

0.14

 seedu

0.14

ccoli

0.13

Activations Density 0.229%

U.S. state names and their associations in the text

No Comments

No Known Activations