INDEX

Explanations

technical terms and abbreviations related to scientific processes or experimental methods

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

entence

-0.15

 GÃ¼n

-0.15

.lu

-0.14

licted

-0.14

.house

-0.14

umas

-0.14

olini

-0.14

 Bros

-0.13

oke

-0.13

imat

-0.13

POSITIVE LOGITS

Éµ

0.16

Eag

0.15

irut

0.14

Ð½Ð¾Ð¿

0.14

_plugins

0.14

assist

0.14

acades

0.14

ìĦľëĬĶ

0.14

istani

0.14

esch

0.13

Activations Density 0.677%

technical terms and abbreviations related to scientific processes or experimental methods

No Comments

No Known Activations