INDEX

Explanations

emotional responses to news or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ø§ÙĦØ§

-0.14

 uncomment

-0.14

alu

-0.13

 Phen

-0.13

ubat

-0.13

ystick

-0.13

.opendaylight

-0.13

Å¡ak

-0.12

æ³ģ

-0.12

Î¼ÏīÏĤ

-0.12

POSITIVE LOGITS

 learn

0.75

 learns

0.71

 learning

0.70

 learned

0.69

learn

0.69

Learn

0.62

 Learn

0.61

 learnt

0.61

_learn

0.58

 Learning

0.57

Activations Density 0.186%

emotional responses to news or events

No Comments

No Known Activations