INDEX

Explanations

phrases expressing evaluations or opinions about experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oeff

-0.19

ayar

-0.17

onta

-0.15

aras

-0.15

ommen

-0.15

arat

-0.15

omik

-0.15

adesh

-0.15

-0.14

arro

-0.14

POSITIVE LOGITS

 nutshell

0.15

Î¹Î¸

0.15

ãĥĥ

0.14

 sweeps

0.14

 sweep

0.14

 Sweep

0.14

 Tide

0.13

rollo

0.13

Lid

0.13

 hell

0.13

Activations Density 0.390%

phrases expressing evaluations or opinions about experiences

No Comments

No Known Activations