INDEX

Explanations

words indicating relationships and emotional connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ãĤ¡

-0.16

iras

-0.15

jen

-0.14

åĢĻ

-0.14

 íĭ

-0.14

ucene

-0.14

oulos

-0.14

ossa

-0.14

 Epoch

-0.13

 reperc

-0.13

POSITIVE LOGITS

 selves

0.20

own

0.20

own

0.18

 ability

0.15

 contribution

0.15

0.14

 involvement

0.14

 approach

0.13

Own

0.13

 role

0.13

Activations Density 0.695%

words indicating relationships and emotional connections

No Comments

No Known Activations