INDEX

Explanations

positive feedback and expressions of satisfaction towards a service or experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ixo

-0.16

otta

-0.14

ditor

-0.14

à¸´à¹Ī

-0.13

romatic

-0.13

éĵº

-0.13

amer

-0.13

icho

-0.13

aman

-0.13

POSITIVE LOGITS

arie

0.16

0.15

osa

0.15

ilies

0.14

RIES

0.14

ario

0.14

va

0.13

_cookie

0.13

 Banc

0.13

iasi

0.13

Activations Density 0.042%

positive feedback and expressions of satisfaction towards a service or experience

No Comments

No Known Activations