INDEX

Explanations

references to full-day experiences or activities

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

olini

-0.16

otime

-0.16

 Bond

-0.16

oire

-0.15

sel

-0.15

.nlm

-0.15

elman

-0.14

ibri

-0.14

 kend

-0.14

UNK

-0.14

POSITIVE LOGITS

yne

0.16

lip

0.15

ocus

0.15

 Blink

0.15

arget

0.15

_traits

0.14

/options

0.14

jiang

0.14

Ð½Ð¸Ð²ÐµÑĢ

0.14

Activations Density 0.013%

references to full-day experiences or activities

No Comments

No Known Activations