INDEX

Explanations

negative descriptors, particularly focusing on feelings of inadequacy and challenges

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

UTTON

-0.17

ÐºÐ°Ð²

-0.17

iso

-0.16

Bez

-0.15

utton

-0.15

inions

-0.15

pose

-0.15

itel

-0.14

alo

-0.14

ê»

-0.14

POSITIVE LOGITS

-Free

0.17

-free

0.17

.Restr

0.16

Å¡t

0.15

 jokes

0.15

rosso

0.14

Pep

0.14

ECTOR

0.14

hack

0.14

nak

0.14

Activations Density 0.913%

negative descriptors, particularly focusing on feelings of inadequacy and challenges

No Comments

No Known Activations