INDEX

Explanations

expressions of desire or requests for specific actions or behaviors

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

Ã³rio

-0.15

illa

-0.15

uesta

-0.14

uilt

-0.14

ibs

-0.14

ui

-0.14

juan

-0.14

 Discovery

-0.14

ready

-0.13

chan

-0.13

POSITIVE LOGITS

CHK

0.15

SGlobal

0.14

ãģªãĤĭ

0.14

 mÃ¶glich

0.14

 Staples

0.14

eric

0.14

Thumb

0.14

ãĥ«ãĤ¯

0.13

efd

0.13

roe

0.13

Activations Density 0.161%

expressions of desire or requests for specific actions or behaviors

No Comments

No Known Activations