INDEX

Explanations

instances of the term "invocation" and its variations, likely in a programming or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

_ep

-0.15

favor

-0.14

semb

-0.14

 Wilde

-0.13

 McGregor

-0.13

aal

-0.13

conexao

-0.13

.cms

-0.13

ÅĽcie

-0.13

à¸Īà¸Ļ

-0.13

POSITIVE LOGITS

TargetException

0.20

inv

0.17

ucher

0.15

figcaption

0.15

ESCO

0.15

urances

0.15

ible

0.15

ixon

0.14

nton

0.14

_DEPRECATED

0.14

Activations Density 0.057%

instances of the term "invocation" and its variations, likely in a programming or technical context

No Comments

No Known Activations