INDEX

Explanations

topics related to writing and communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

angel

-0.17

ichen

-0.16

feed

-0.14

ich

-0.14

Feedback

-0.14

åģı

-0.13

 undert

-0.13

erman

-0.13

 Guth

-0.13

 Burgess

-0.13

POSITIVE LOGITS

 ucwords

0.15

overrides

0.15

ilir

0.15

RowIndex

0.15

leitung

0.14

 Ð½Ð°ÑĤÑĥ

0.14

ç¤¾

0.14

kses

0.14

ÙĪÙĦÙĪ

0.14

ElementException

0.14

Activations Density 0.287%

topics related to writing and communication

No Comments

No Known Activations