INDEX

Explanations

occurrences of the word "About," indicating a focus on introductory or descriptive content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

enting

-0.18

aid

-0.15

sg

-0.15

akis

-0.14

Hij

-0.14

 architectural

-0.14

æ

-0.14

ØªØ§ÙĨ

-0.14

 dÃŃ

-0.14

angen

-0.13

POSITIVE LOGITS

bÄĽ

0.14

.createComponent

0.14

agas

0.14

Lazy

0.13

Vectorizer

0.13

endale

0.13

íĹ¤

0.13

Å¯r

0.13

Activations Density 0.017%

occurrences of the word "About," indicating a focus on introductory or descriptive content

No Comments

No Known Activations