INDEX

Explanations

text discussing the complexities and ambiguities surrounding authorship and identity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Å¡ov

-0.17

 Ø¯ÛĮÚ¯Ø±ÛĮ

-0.14

 outra

-0.14

 MÃ¶glich

-0.13

owe

-0.13

ISIBLE

-0.13

two

-0.13

 Another

-0.13

 three

-0.13

isd

-0.13

POSITIVE LOGITS

 certain

0.50

 particular

0.48

æŁĲ

0.38

 specific

0.35

 certains

0.35

Certain

0.34

 various

0.33

 each

0.33

any

0.32

 Certain

0.31

Activations Density 1.047%

text discussing the complexities and ambiguities surrounding authorship and identity in various contexts

No Comments

No Known Activations