INDEX

Explanations

references to numerology and its calculations related to personal details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

akis

-0.16

Î»Î¯Î¿Ïħ

-0.16

liÄį

-0.15

egasus

-0.15

-0.14

ìĿ´íĦ°

-0.14

ãĥ«ãĥķ

-0.14

iej

-0.14

eras

-0.14

_PLATFORM

-0.14

POSITIVE LOGITS

 chod

0.17

oh

0.16

qv

0.15

 matter

0.14

ystate

0.14

ÐµÐ²ÐµÑĢ

0.14

 Slate

0.14

oval

0.14

((↵

0.13

Oh

0.13

Activations Density 0.111%

references to numerology and its calculations related to personal details

No Comments

No Known Activations