INDEX

Explanations

terms related to web references and social context within a digital or service-oriented environment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

orb

-0.16

enor

-0.15

gue

-0.14

æĶ¯

-0.14

enant

-0.14

Kel

-0.14

elter

-0.14

ACE

-0.14

 Shrine

-0.14

tered

-0.14

POSITIVE LOGITS

Sol

0.18

Sol

0.17

_sol

0.16

 soluble

0.15

sol

0.15

Da

0.15

 solvent

0.15

ÑģÐ¾Ð»

0.15

 Vern

0.15

sol

0.15

Activations Density 0.030%

terms related to web references and social context within a digital or service-oriented environment

No Comments

No Known Activations