INDEX

Explanations

terms related to technical processes and systems, particularly in engineering and scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

bestos

-0.16

/her

-0.15

-ln

-0.14

mania

-0.14

criptive

-0.13

 Ð¶Ðµ

-0.13

cratch

-0.13

afd

-0.13

abei

-0.13

ayas

-0.12

POSITIVE LOGITS

atics

0.15

lessly

0.15

ings

0.14

edBy

0.14

0.13

amentals

0.13

tures

0.13

edly

0.13

Activations Density 1.922%

terms related to technical processes and systems, particularly in engineering and scientific contexts

No Comments

No Known Activations