INDEX

Explanations

terms related to financial or gaming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ugar

-0.15

ToFit

-0.14

ilight

-0.13

pb

-0.13

 carriage

-0.13

nutrition

-0.13

fm

-0.13

lazy

-0.13

 Harmon

-0.12

loo

-0.12

POSITIVE LOGITS

presso

0.16

otine

0.15

Scaler

0.15

igon

0.15

INY

0.15

etler

0.14

.opendaylight

0.14

riet

0.14

berman

0.14

Activations Density 0.002%

terms related to financial or gaming contexts

No Comments

No Known Activations