INDEX

Explanations

technical terms and coding elements related to software or web development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

à¥įà¤°à¤¦

-0.18

 retros

-0.16

æ¢¨

-0.15

 springfox

-0.14

raf

-0.14

rosso

-0.14

assa

-0.14

senal

-0.14

riteln

-0.14

 Restoration

-0.14

POSITIVE LOGITS

Re

1.09

Re

0.98

-Re

0.88

_Re

0.82

RE

0.79

re

0.79

-re

0.78

_re

0.76

.re

0.74

.Re

0.72

Activations Density 0.154%

technical terms and coding elements related to software or web development

No Comments

No Known Activations