INDEX

Explanations

programming terms and functions related to events and data types

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

Ð¾Ð´Ð¾

-0.15

ŀĭ

-0.14

ingo

-0.14

arkan

-0.14

NavItem

-0.13

(Collision

-0.13

 Levine

-0.13

ctic

-0.13

/MIT

-0.13

åĶ

-0.13

POSITIVE LOGITS

oval

0.17

 TMPro

0.15

 nackte

0.15

iley

0.15

erie

0.14

Ð¼Ð°Ñħ

0.14

inox

0.14

ove

0.14

kad

0.13

.qu

0.13

Activations Density 0.067%

programming terms and functions related to events and data types

No Comments

No Known Activations