INDEX

Explanations

occurrences of function and object definitions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ãĥĪãĥ«

-0.17

å¯

-0.15

ãĥ³ãĤ°

-0.14

istrovstvÃŃ

-0.14

Ø³Ø§Ùħ

-0.14

ÑģÐµÑĢ

-0.14

ainers

-0.14

=============

-0.14

 Gest

-0.13

 Shapiro

-0.13

POSITIVE LOGITS

0.27

0.22

0.21

0.17

iano

0.16

enu

0.16

ãĢĢãĢĢãĢĢ

0.15

undi

0.15

Inn

0.15

rx

0.15

Activations Density 0.063%

occurrences of function and object definitions in code

No Comments

No Known Activations