INDEX

Explanations

terms related to rules, limitations, and specifications 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

middlewares

-0.15

Expected

-0.14

efa

-0.14

etu

-0.14

omal

-0.14

 Expected

-0.14

 Minimal

-0.14

 little

-0.14

 Estimated

-0.14

POSITIVE LOGITS

 maximum

0.46

maximum

0.42

MAX

0.40

max

0.40

Maximum

0.40

 Maximum

0.39

 ìµľëĮĢ

0.38

max

0.37

MAX

0.36

Max

0.34

Activations Density 0.154%

terms related to rules, limitations, and specifications in various contexts

No Comments

No Known Activations