INDEX

Explanations

references to academic or technical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 exercise

-0.10

 attraction

-0.10

 presence

-0.10

 spin

-0.10

 collective

-0.10

 proof

-0.10

 stretch

-0.10

 execution

-0.10

 realization

-0.10

 engagement

-0.10

POSITIVE LOGITS

 rÅ¯z

0.14

 chtÄĽ

0.13

 Äįlov

0.12

ģm

0.12

 udÃ¡l

0.12

 prÅ¯m

0.12

 Äįty

0.12

.ISupportInitialize

0.11

¢åįķ

0.11

 ê°¤ë¡ľê·¸

0.11

Activations Density 19.630%

references to academic or technical information

No Comments

No Known Activations