INDEX

Explanations

concepts and terms related to affirmations and positive reinforcement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

è©

-0.16

 Fletcher

-0.15

liness

-0.15

oro

-0.15

aps

-0.14

uw

-0.14

apor

-0.14

aab

-0.13

ROL

-0.13

 Solic

-0.13

POSITIVE LOGITS

Zum

0.14

ToPoint

0.13

 Evet

0.13

aptop

0.13

alie

0.13

 êµ

0.13

etheus

0.13

.KeyPress

0.13

IEL

0.13

ource

0.13

Activations Density 0.006%

concepts and terms related to affirmations and positive reinforcement

No Comments

No Known Activations