INDEX

Explanations

references to places, names, and numbers associated with locations and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ise

-0.16

oup

-0.14

ibo

-0.14

atic

-0.14

unk

-0.14

pha

-0.14

GP

-0.14

pts

-0.13

 Chow

-0.13

iqu

-0.13

POSITIVE LOGITS

leftright

0.15

ModelIndex

0.15

.getStatusCode

0.14

æĻ´

0.14

ÏĨÎ¹

0.14

Ø§ÙĦØ¹

0.14

Ð¸Ð½Ð¾Ð¹

0.13

 à¤ķà¤¡

0.13

nech

0.13

linky

0.13

Activations Density 0.026%

references to places, names, and numbers associated with locations and publications

No Comments

No Known Activations