INDEX

Explanations

positive affirmations and descriptions of experiences or qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Emmy

-0.16

-0.14

outh

-0.14

abee

-0.14

aramel

-0.13

 REPL

-0.13

POSITIVE LOGITS

ÑĨÐ¸

0.17

ithe

0.16

atti

0.14

.mozilla

0.13

ceptive

0.13

Å¡ek

0.13

ackbar

0.13

_continuous

0.13

 circ

0.13

Ð¾Ñī

0.13

Activations Density 0.273%

positive affirmations and descriptions of experiences or qualities

No Comments

No Known Activations