INDEX

Explanations

phrases and concepts related to choices and decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Fischer

-0.16

onto

-0.15

endale

-0.14

UDO

-0.14

Wo

-0.14

 comm

-0.14

udo

-0.14

 Buch

-0.13

adj

-0.13

uo

-0.13

POSITIVE LOGITS

erken

0.15

bz

0.15

HeaderView

0.15

InView

0.15

 Magnum

0.14

ëł¨

0.14

 khÃŃ

0.14

ForResult

0.14

tle

0.14

 Dome

0.14

Activations Density 0.007%

phrases and concepts related to choices and decision-making

No Comments

No Known Activations