INDEX

Explanations

significant numerical values, particularly those associated with events, characters, and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

abay

-0.18

Animating

-0.17

NotExist

-0.15

Traits

-0.15

ToF

-0.14

ãģĭãĤĬ

-0.14

rava

-0.14

acock

-0.14

.elem

-0.13

POSITIVE LOGITS

0.15

buc

0.15

,cp

0.15

enville

0.14

haar

0.14

zing

0.14

oples

0.14

ÑĦÐµÑĢ

0.14

adc

0.14

neas

0.14

Activations Density 0.003%

significant numerical values, particularly those associated with events, characters, and locations

No Comments

No Known Activations