INDEX

Explanations

phrases indicating ongoing processes or statuses related to development, operation, or existence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

onium

-0.18

cu

-0.15

now

-0.15

 Å¡to

-0.14

Hy

-0.14

à¥įà¤ªà¤¤

-0.14

ÐµÑĢÐ¾Ð¼

-0.14

ein

-0.13

 convinced

-0.13

ouro

-0.13

POSITIVE LOGITS

 since

0.17

ebra

0.16

ityEngine

0.16

iox

0.15

utter

0.15

uest

0.14

iffer

0.14

sip

0.14

edom

0.14

iversit

0.14

Activations Density 0.171%

phrases indicating ongoing processes or statuses related to development, operation, or existence

No Comments

No Known Activations