INDEX

Explanations

phrases that indicate intent or purpose related to achieving specific goals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

vert

-0.15

itan

-0.14

upa

-0.14

atab

-0.14

Å¼

-0.13

à¹Īà¸¥à¸°

-0.13

ÑĽ

-0.13

 Rapid

-0.13

ab

-0.13

POSITIVE LOGITS

ardon

0.17

razier

0.16

Nad

0.16

nad

0.15

esses

0.15

ilogy

0.15

arkers

0.15

ÐµÐ¼Ð°ÑĤÐ¸

0.14

iras

0.14

 Suff

0.14

Activations Density 0.010%

phrases that indicate intent or purpose related to achieving specific goals

No Comments

No Known Activations