INDEX

Explanations

technical terms and components related to coding and machine learning systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

iple

-0.16

Canonical

-0.15

íĴį

-0.14

aber

-0.14

 ment

-0.14

trail

-0.14

issen

-0.13

enco

-0.13

_PRED

-0.13

ersiz

-0.13

POSITIVE LOGITS

sonian

0.15

ounces

0.15

ounce

0.14

umblr

0.14

Ã¼ns

0.14

ilig

0.14

OUNCE

0.13

ewood

0.13

 alphabetical

0.13

Activations Density 0.507%

technical terms and components related to coding and machine learning systems

No Comments

No Known Activations