INDEX

Explanations

conversational phrases that express agreement, reflection, or surprise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

:System

-0.16

 ActionTypes

-0.15

erais

-0.15

æľīçļĦ

-0.14

ãģĭãĤı

-0.14

utf

-0.14

 Dish

-0.14

.charCodeAt

-0.14

ynth

-0.14

gr

-0.13

POSITIVE LOGITS

 Linden

0.16

irma

0.16

Å¾e

0.15

asher

0.15

ihu

0.14

asca

0.14

ÏĢÎ¿Ïį

0.14

iene

0.14

elon

0.14

ih

0.14

Activations Density 0.224%

conversational phrases that express agreement, reflection, or surprise

No Comments

No Known Activations