INDEX

Explanations

references to job positions and career advancements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rompt

-0.16

ahoma

-0.15

ycz

-0.15

inery

-0.15

ÑĢÑİ

-0.14

idden

-0.14

 procur

-0.14

 svÄĽ

-0.14

åĬŁ

-0.13

olicy

-0.13

POSITIVE LOGITS

 circulation

0.43

 newspaper

0.40

 papers

0.39

 newspapers

0.36

 Newspaper

0.35

 circ

0.35

 Newsp

0.35

 paper

0.35

 Circ

0.34

papers

0.33

Activations Density 0.117%

references to job positions and career advancements

No Comments

No Known Activations