INDEX

Explanations

words related to specific roles, positions, or titles in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.16

.ba

-0.15

-0.14

 cargo

-0.14

TES

-0.14

 Blanco

-0.14

Lav

-0.14

eno

-0.14

cen

-0.14

 wound

-0.13

POSITIVE LOGITS

à¸Ľà¸£à¸°à¸¡

0.17

wig

0.16

/Dk

0.15

ÙĪØ§Ùĩ

0.15

.libs

0.15

ssql

0.15

ibernate

0.14

ektir

0.14

isor

0.14

asurer

0.14

Activations Density 0.253%

words related to specific roles, positions, or titles in various contexts

No Comments

No Known Activations